United States

This work studies temporal reading comprehension (TRC), which reads a free-text passage and answers temporal ordering questions. Precise question understanding is critical for temporal reading comprehension. For example, the question &quot;What happened before the victory&quot; and &quot;What happened after the victory&quot; share almost all words except one, while their answers are totally different. Moreover, even if two questions query about similar temporal relations, different varieties might also lead to various answers. For example, although both the question &quot;What usually happened during the press release?&quot; and &quot;What might happen during the press release&quot; query events which happen after &quot;the press release&quot;, they convey divergent semantics.
To this end, we propose a novel reading comprehension approach with precise question understanding. Specifically, a temporal ordering question is embedded into two vectors to capture the referred event and the temporal relation. Then we evaluate the temporal relation between candidate events and the referred event based on that. Such fine-grained representations offer two benefits. First, it enables a better understanding of the question by focusing on different elements of a question. Second, it provides good interpretability when evaluating temporal relations. Furthermore, we also harness an auxiliary contrastive loss for representation learning of temporal relations, which aims to distinguish relations with subtle but critical changes. 
The proposed approach outperforms strong baselines and achieves state-of-the-art performance on the TORQUE dataset. It also increases the accuracy of four pre-trained language models (BERT base, BERT large, RoBERTa base, and RoBETRa large), demonstrating its generic effectiveness on divergent models.

NAACL 2022

Understand before Answer: Improve Temporal Reading Comprehension via Precise Question Understanding

temporal ordering

machine reading comprehension

contrastive learning

**Welcome to EMNLP 2023!**

On behalf of the EMNLP 2023 Organizing Committee, I extend a warm and heartfelt welcome to all of you to the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP). It is with immense pleasure and excitement that we gather here in Singapore, a vibrant hub of innovation and technological advancement.

The conference program is packed with insightful presentations, thought-provoking workshops, and engaging networking opportunities. In addition to the technical sessions, we have also planned several social events that will provide you with the opportunity to connect with your colleagues.

The conference is held in person at the Resorts World Convention Centre in Singapore, and available on-line with the help of Underline.

For those in Singapore, I hope that you will find time to explore the exciting Sentosa Island, Gardens by the Bay, Singapore Botanic Gardens and the many other attractions unique to Singapore.

Of course, we are grateful to our sponsors and partners for their generous support of EMNLP 2023, whose contributions make it possible for us to host this world-class event.

Yuji Matsumoto (RIKEN AIP) 
EMNLP 2023 General Chair

To access the **EMNLP 2023** event page on Underline, you need to register for the Conference. 
Please follow **[this link](https://2023.emnlp.org/registration/)** for more details.

EMNLP 2023

EMNLP 2023 took place in Singapore from Dec 6th to Dec 10th, 2023.

This work studies temporal reading comprehension (TRC), which reads a free-text passage and answers temporal ordering questions. Precise question understanding is critical for temporal reading comprehension. For example, the question "What happened before the victory" and "What happened after the victory" share almost all words except one, while their answers are totally different. Moreover, even if two questions query about similar temporal relations, different varieties might also lead to various answers. For example, although both the question "What usually happened during the press release?" and "What might happen during the press release" query events which happen after "the press release", they convey divergent semantics.
To this end, we propose a novel reading comprehension approach with precise question understanding. Specifically, a temporal ordering question is embedded into two vectors to capture the referred event and the temporal relation. Then we evaluate the temporal relation between candidate events and the referred event based on that. Such fine-grained representations offer two benefits. First, it enables a better understanding of the question by focusing on different elements of a question. Second, it provides good interpretability when evaluating temporal relations. Furthermore, we also harness an auxiliary contrastive loss for representation learning of temporal relations, which aims to distinguish relations with subtle but critical changes. 
The proposed approach outperforms strong baselines and achieves state-of-the-art performance on the TORQUE dataset. It also increases the accuracy of four pre-trained language models (BERT base, BERT large, RoBERTa base, and RoBETRa large), demonstrating its generic effectiveness on divergent models.

poster

## Welcome to NAACL 2022!
The Annual Meeting of the North American Chapter of the Association for Computational Linguistics (NAACL) is taking place July 10-15, 2022 as a hybrid event, in Seattle, WA and online. We are happy to welcome all of you to conference! 
 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, keynote presentations, a plenary panel on the place of linguistics and symbolic structures in NLP, and an Industrial Track panel on Careers in NLP.
 
Posters (including Findings of NAACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop and will have an oral session and a poster session.
 
The program also features 6 Tutorials and 26 Workshops.
 
 We wish you a wonderful conference!
 
[The NAACL 2022 Organizing Committee](https://2022.naacl.org/committees/organization/)

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

Argument classification is at the core of Semantic Role Labeling. Given a sentence and the predicate, a semantic role label is assigned to each argument of the predicate. While semantic roles come with meaningful definitions, existing work has treated them as symbolic. Learning symbolic labels usually requires ample training data, which is frequently unavailable due to the cost of annotation. We instead propose to retrieve and leverage the definitions of these labels from the annotation guidelines. For example, the verb predicate "work" has arguments defined as "worker", "job", "employer", etc. Our model achieves state-of-the-art performance on the CoNLL09 dataset injected with label definitions given the predicate senses. The performance improvement is even more pronounced in low-resource settings when training data is scarce.

Label Definitions Improve Semantic Role Labeling

As a fundamental task in opinion mining, aspect and opinion co-extraction aims to identify the aspect terms and opinion terms in reviews. However, due to the lack of fine-grained annotated resources, it is hard to train a robust model for many domains. To alleviate this issue, unsupervised domain adaptation is proposed to transfer knowledge from a labeled source domain to an unlabeled target domain. In this paper, we propose a new Generative Cross-Domain Data Augmentation framework for unsupervised domain adaptation. The proposed framework is aimed to generate target-domain data with fine-grained annotation by exploiting the labeled data in the source domain. Specifically, we remove the domain-specific segments in a source-domain labeled sentence, and then use this as input to a pre-trained sequence-to-sequence model BART to simultaneously generate a target-domain sentence and predict the corresponding label for each word. Experimental results on three datasets demonstrate that our approach is more effective than previous domain adaptation methods.

Generative Cross-Domain Data Augmentation for Aspect and Opinion Co-Extraction

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment classification task. Most recent efforts adopt pre-trained model to classify the sentences with aspects. However, the aspect sentiment bias from pre-trained model brings some noise to the ABSA task. Besides, traditional methods using cross-entropy loss are hard to find the potential associations between sentiment polarities. In this work, we analyze the ABSA task from a novel cognition perspective: humans can often judge the sentiment of an aspect even if they do not know what the aspect is. Moreover, it is easier to distinguish positive and negative sentiments than others for human beings because positive and negative are two opposite sentiments. To this end, we propose a no-aspect differential sentiment (NADS) framework for the ABSA task. We first design a no-aspect template by replacing the aspect with a special unbiased character to eliminate the sentiment bias and obtain a stronger representation. To better get the benefits from the template, we adopt contrastive learning between the no-aspect template and the original sentence. Then we propose a differential sentiment loss instead of the cross-entropy loss to better classify the sentiments by distinguishing the different distances between sentiments. Our proposed model is a general framework and can be combined with almost all traditional ABSA methods. Experiments on SemEval 2014 show that our framework is still able to predict the sentiment of the aspect even we don't konw what the aspect is. Moreover, our NADS framework boosts three typical ABSA methods and achieves state-of-the-art performance.

Aspect Is Not You Need: No-aspect Differential Sentiment Framework for Aspect-based Sentiment Analysis

Deep acoustic models represent linguistic information based on massive amounts of data. Unfortunately, for regional languages and dialects such resources are mostly not available. However, deep acoustic models might have learned linguistic information that transfers to low-resource languages. In this study, we evaluate whether this is the case through the task of distinguishing low-resource (Dutch) regional varieties. By extracting embeddings from the hidden layers of various wav2vec 2.0 models (including new models which are pre-trained and/or fine-tuned on Dutch) and using dynamic time warping, we compute pairwise pronunciation differences averaged over 10 words for over 100 individual dialects from four (regional) languages. We then cluster the resulting difference matrix in four groups and compare these to a gold standard, and a partitioning on the basis of comparing phonetic transcriptions. Our results show that acoustic models outperform the (traditional) transcription-based approach without requiring phonetic transcriptions, with the best performance achieved by the multilingual XLSR-53 model fine-tuned on Dutch. On the basis of only six seconds of speech, the resulting clustering closely matches the gold standard.

Quantifying Language Variation Acoustically with Few Resources

Due to the dialogue characteristics of unstruc- tured contexts and multi-parties with first- person perspective, many successful text sum- marization works have failed when dealing with dialogue summarization. In dialogue sum- marization task, the input dialogue is usually spoken style with ellipsis and co-references but the output summaries are more formal and com- plete. Therefore, the dialogue summarization model should be able to complete the ellipsis content and co-reference information and then produce a suitable summary accordingly. How- ever, the current state-of-the-art models pay more attention on the topic or structure of sum- mary, rather than the consistency of dialogue summary with its input dialogue context, which may suffer from the personal and logical incon- sistency problem. In this paper, we propose a new model, named ReWriteSum, to tackle this problem. Firstly, an utterance rewriter is conducted to complete the ellipsis content of dialogue content and then obtain the rewriting utterances. Then, the co-reference data aug- mentation mechanism is utilized to replace the referential person name with its specific name to enhance the personal information. Finally, the rewriting utterances and the co-reference re- placement data are used in the standard BART model. Experimental results on both SAMSum and DialSum datasets show that our ReWrite- Sum significantly outperforms baseline models, in terms of both metric-based and human evalu- ations. Further analysis on multi-speakers also shows that ReWriteSum can obtain relatively higher improvement with more speakers, vali- dating the correctness and property of ReWrite- Sum.

From spoken dialogue to formal summary: An utterance rewriting for dialogue summarization

The last decade has witnessed a surge in the interaction of people through social networking platforms. While there are several positive aspects of these social platforms, their proliferation has led them to become the breeding ground for cyber-bullying and hate speech. Recent advances in NLP have often been used to mitigate the spread of such hateful content.
Since the task of hate speech detection is usually applicable in the context of social networks, we introduce CRUSH, a framework for hate speech detection using User Anchored self-supervision and contextual regularization.
Our proposed approach secures ~1-12% improvement in test set metrics over best performing previous approaches on two types of tasks and multiple popular English language social networking datasets.

CRUSH: Contextually Regularized and User anchored Self-supervised Hate speech Detection

Complaining is a speech act that expresses a negative inconsistency between reality and human’s expectations. While prior studies mostly focus on identifying the existence or the type of complaints, in this work, we present the ﬁrst study in computational linguistics of measuring the intensity of complaints from text. Analyzing complaints from such perspective is particularly useful, as complaints of certain degrees may cause severe consequences for companies or organizations. We ﬁrst collect 3,103 posts about complaints in education domain from Weibo, a popular Chinese social media platform. These posts are then annotated with complaints intensity scores using Best-Worst Scaling (BWS) method. We show that complaints intensity can be accurately estimated by computational models with best mean square error achieving 0.11. Furthermore, we conduct a comprehensive linguistic analysis around complaints, including the connections between complaints and sentiment, and a cross-lingual comparison for complaints expressions used by Chinese and English speakers. We ﬁnally show that our complaints intensity scores can be incorporated for better estimating the popularity of posts on social media.

Analyzing the Intensity of Complaints on Social Media

Internet memes have emerged as an increasingly popular means of communication on the web. Although memes are typically intended to elicit humour, they have been increasingly used to spread hatred, trolling, and cyberbullying, as well as to target specific individuals, communities, or society on political, socio-cultural, and psychological grounds. While previous work has focused on detecting harmful, hateful, and offensive memes in general, identifying whom these memes attack (i.e., the `victims') remains a challenging and underexplored area. We attempt to address this problem in this paper. To this end, we create a dataset in which we annotate each meme with its victim(s) such as the name of the targeted person(s), organization(s), and community(ies). We then propose DISARM (Detecting vIctimS targeted by hARmful Memes), a framework that uses named-entity recognition and person identification to detect all entities a meme is referring to, and then, incorporates a novel contextualized multimodal deep neural network to classify whether the meme intends to harm these entities. We perform several systematic experiments on three different test sets, corresponding to entities that are (i) all seen while training, (ii) not seen as a harmful target while training, and (iii) not seen at all while training. The evaluation shows that DISARM significantly outperforms 10 unimodal and multimodal systems. Finally, we demonstrate that DISARM is interpretable and comparatively more generalizable and that it can reduce the relative error rate of harmful target identification by up to 9 % absolute over multimodal baseline systems.

DISARM: Detecting the Victims Targeted by Harmful Memes

Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained language models. However, intermediate layer distillation suffers from excessive computational burdens and engineering efforts required for setting up a proper layer  mapping. To address these problems, we propose a RAndom Intermediate Layer Knowledge Distillation (RAIL-KD) approach in which, intermediate layers from the teacher model are selected randomly to be distilled into the intermediate layers of the student model. This randomized selection enforces that all teacher layers are taken into account in the training process, while reducing the computational cost of intermediate layer distillation. Also, we show that it acts as a regularizer for improving the generalizability of the student model. We perform extensive experiments on GLUE tasks as well as on out-of-domain test sets. We show that our proposed RAIL-KD approach outperforms other state-of-the-art intermediate layer KD methods considerably in both performance and training-time.

RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation

The Transformer architecture continues to show remarkable performance gains in many Natural Language Processing tasks. However, obtaining such state-of-the-art performance in different tasks requires fine-tuning the same model separately for each task. Clearly, such an approach is demanding in terms of both memory requirements and computing power. In this paper, aiming to improve training efficiency across multiple tasks, we propose to collectively factorize the weighs of the multi-head attention module of a pre-trained Transformer. We test our proposed method on finetuning multiple natural language understanding tasks by employing BERT-Large as an instantiation of the Transformer and the GLUE as the evaluation benchmark.  Experimental results show that our method requires training and storing only 1\% of the initial model parameters for each task and matches or improves the original fine-tuned model's performance for each task while effectively decreasing the parameter requirements by two orders of magnitude. Furthermore, compared to well-known adapter-based alternatives on the GLUE benchmark, our method consistently reaches the same levels of performance while requiring approximately four times fewer total and trainable parameters per task.

Downloads

Next from NAACL 2022

Label Definitions Improve Semantic Role Labeling

Similar lecture

Fusing Temporal Graphs into Transformers for Time-Sensitive Question Answering