Dominican Republic

Pre-trained language models (PTLMs) have achieved impressive performance on commonsense inference benchmarks, but their ability to employ commonsense to make robust inferences, which is crucial for effective communications with humans, is debated. In the pursuit of advancing fluid human-AI communication, we propose a new challenge, RICA: Robust Inference using Commonsense Axioms, that evaluates robust commonsense inference despite textual perturbations. To generate data for this challenge, we develop a systematic and scalable procedure using commonsense knowledge bases and probe PTLMs across two different evaluation settings. Extensive experiments on our generated probe sets with more than 10k statements show that PTLMs perform no better than random guessing on the zero-shot setting, are heavily impacted by statistical biases, and are not robust to perturbation attacks. We also find that fine-tuning on similar statements offer limited gains, as PTLMs still fail to generalize to unseen inferences. Our new large-scale benchmark exposes a significant gap between PTLMs and human-level language understanding and offers a new challenge for PTLMs to demonstrate commonsense.

EMNLP 2021

RICA: Evaluating Robust Inference Capabilities Based on Commonsense Axioms

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible. The experience for on-site participants would closely approximate a normal pre-COVID *ACL conference, with 5-6 thematically organized parallel sessions and live Q/A and interactive discussion immediately after the talks. Presentations by virtual participants will be equitably interleaved with those of on-site participants, projected on the auditorium screens as if on-site, and also followed immediately by live Q/A and interactive discussion at a time during reasonable waking hours for the virtual presenter. For all participants, on-site and virtual, who are unable to attend a session due to either time-zone issues or because they are participating in another session live, talk recordings and slides will be available online at a minimum after the live presentation (and in many cases before as well), and questions may be submitted in advance on session-specific discussion boards and answered live in session with the usual visual aids if desired.

<iframe style="width:700px;height:400px" src="https://online.fliphtml5.com/ebtyf/ceby/"  seamless="seamless" scrolling="no" frameborder="0" allowtransparency="true" allowfullscreen="true" ></iframe>

Please Note: The EMNLP registration system is not currently connected to the underline site as we are still in the process of building out EMNLP 2021. You will receive access instructions from underline the week of November 1st. 

Access is given only to EMNLP upon registration, if you have not registered please do so [here](https://2021.emnlp.org/registration).

Registered attendees will receive access the week of November 1st.

EMNLP 2021 is planned to be a hybrid event in Punta Cana, Dominican Republic, with both on-site and fully virtual participation possible.

technical paper

Image captioning has conventionally relied on reference-based automatic evaluations, where machine captions are compared against captions written by humans. This is in contrast to the reference-free manner in which humans assess caption quality. In this paper, we report the surprising empirical finding that CLIP (Radford et al., 2021), a cross-modal model pretrained on 400M image+caption pairs from the web, can be used for robust automatic evaluation of image captioning without the need for references. Experiments spanning several corpora demonstrate that our new reference-free metric, CLIPScore, achieves the highest correlation with human judgements, outperforming existing reference-based metrics like CIDEr and SPICE. Information gain experiments demonstrate that CLIPScore, with its tight focus on image-text compatibility, is complementary to existing reference-based metrics that emphasize text-text similarities. Thus, we also present a reference-augmented version, RefCLIPScore, which achieves even higher correlation. Beyond literal description tasks, several case studies reveal domains where CLIPScore performs well (clip-art images, alt-text rating), but also where it is relatively weaker in comparison to reference-based metrics, e.g., news captions that require richer contextual knowledge.

CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Building compositional explanations requires models to combine two or more facts that, together, describe why the answer to a question is correct. Typically, these "multi-hop" explanations are evaluated relative to one (or a small number of) gold explanations. In this work, we show these evaluations substantially underestimate model performance, both in terms of the relevance of included facts, as well as the completeness of model-generated explanations, because models regularly discover and produce valid explanations that are different than gold explanations. To address this, we construct a large corpus of 126k domain-expert (science teacher) relevance ratings that augment a corpus of explanations to standardized science exam questions, discovering 80k additional relevant facts not rated as gold. We build three strong models based on different methodologies (generation, ranking, and schemas), and empirically show that while expert-augmented ratings provide better estimates of explanation quality, both original (gold) and expert-augmented automatic evaluations still substantially underestimate performance by up to 36% when compared with full manual expert judgements, with different models being disproportionately affected. This poses a significant methodological challenge to accurately evaluating explanations produced by compositional reasoning models.

On the Challenges of Evaluating Compositional Explanations in Multi-Hop Inference: Relevance, Completeness, and Expert Ratings

Stories and narratives are composed based on a variety of events. Understanding how these events are semantically related to each other is the essence of reading comprehension. Recent event-centric reading comprehension datasets focus on either event arguments or event temporal commonsense. Although these tasks evaluate machines' ability of narrative understanding, human-like reading comprehension requires the capability to process event-based semantics beyond arguments and temporal commonsense. For example, to understand causality between events, we need to infer motivations or purposes; to understand event hierarchy, we need to parse the composition of events. To facilitate these tasks, we introduce ESTER, a comprehensive machine reading comprehension (MRC) dataset for Event Semantic Relation Reasoning. We study the five most commonly used event semantic relations and formulate them as question answering tasks. Experimental results show that the current SOTA systems achieve 60.5%, 57.8%, and 76.3% for event-based F1, token-based F1, and HIT@1 scores respectively, which are significantly below human performances.

ESTER: A Machine Reading Comprehension Dataset for Reasoning about Event Semantic Relations

With the explosive growth of livestream broadcasting, there is an urgent need for new summarization technology that enables us to create a preview of streamed content and tap into this wealth of knowledge. However, the problem is nontrivial due to the informal nature of spoken language. Further, there has been a shortage of annotated datasets that are necessary for transcript summarization. In this paper, we present StreamHover, a framework for annotating and summarizing livestream transcripts. With a total of over 500 hours of videos annotated with both extractive and abstractive summaries, our benchmark dataset is significantly larger than currently existing annotated corpora. We explore a neural extractive summarization model that leverages vector-quantized variational autoencoder to learn latent vector representations of spoken utterances and identify salient utterances from the transcripts to form summaries. We show that our model generalizes better and improves performance over strong baselines. The results of this study provide an avenue for future research to improve summarization solutions for efficient browsing of livestreams.

StreamHover: Livestream Transcript Summarization and Annotation

Recent efforts to develop deep learning mod- els for text generation tasks such as extractive and abstractive summarization have resulted in state-of-the-art performances on various datasets. However, obtaining the best model configuration for a given dataset requires an extensive knowledge of deep learning specifics like model architecture, tuning parameters etc., and is often extremely challenging for a non-expert. In this paper, we propose methods to automatically create deep learning models for the tasks of extractive and abstractive text summarization. Based on the recent advances in Automated Machine Learning and the success of large language models such as BERT and GPT-2 in encoding knowledge, we use a combination of Neural Architecture Search (NAS) and Knowledge Distillation (KD) techniques to perform model search and compression using the vast knowl- edge provided by these language models to develop smaller, customized models for any given dataset. We present extensive empirical results to illustrate the effectiveness of our model creation methods in terms of inference time and model size, while achieving near state-of-the-art performances in terms of accuracy across a range of datasets.

AUTOSUMM: Automatic Model Creation for Text Summarization

Human evaluation for summarization tasks is reliable but brings in issues of reproducibility and high costs. Automatic metrics are cheap and reproducible but sometimes poorly correlated with human judgment. In this work, we propose flexible semiautomatic to automatic summary evaluation metrics, following the Pyramid human evaluation method. Semi-automatic Lite2Pyramid retains the reusable human-labeled Summary Content Units (SCUs) for reference(s) but replaces the manual work of judging SCUs' presence in system summaries with a natural language inference (NLI) model. Fully automatic Lite3Pyramid further substitutes SCUs with automatically extracted Semantic Triplet Units (STUs) via a semantic role labeling (SRL) model. Finally, we propose in-between metrics, Lite2.xPyramid, where we use a simple regressor to predict how well the STUs can simulate SCUs and retain SCUs that are more difficult to simulate, which provides a smooth transition and balance between automation and manual evaluation. Comparing to 15 existing metrics, we evaluate human-metric correlations on 3 existing meta-evaluation datasets and our newly-collected PyrXSum (with 100/10 XSum examples/systems). It shows that Lite2Pyramid consistently has the best summary-level correlations; Lite3Pyramid works better than or comparable to other automatic metrics; Lite2.xPyramid trades off small correlation drops for larger manual effort reduction, which can reduce costs for future data collection.

Finding a Balanced Degree of Automation for Summary Evaluation

Commonsense Question Answering is an important natural language processing (NLP) task that aims to predict the correct answer to a question through commonsense reasoning. Previous studies utilize pre-trained models on large-scale corpora such as BERT, or perform reasoning on knowledge graphs. However, these methods do not explicitly model the relations that connect entities, which are informational and can be used to enhance reasoning. To address this issue, we propose a relation-aware reasoning method. Our method uses a relation-aware graph neural network to capture the rich contextual information from both entities and relations. Compared with methods that use fixed relation embeddings from pre-trained models, our model dynamically updates relations with contextual information from a multi-source subgraph, built from multiple external knowledge sources. The enhanced representations of relations are then fed to a bidirectional reasoning module. A bidirectional attention mechanism is applied between the question sequence and the paths that connect entities, which provides us with transparent interpretability. Experimental results on the CommonsenseQA dataset illustrate that our method results in significant improvements over the baselines while also providing clear reasoning paths.

Relation-aware Bidirectional Path Reasoning for Commonsense Question Answering

Recent work indicated that pretrained language models (PLMs) such as BERT and RoBERTa can be transformed into effective sentence and word encoders even via simple self-supervised techniques. Inspired by this line of work, in this paper we propose a fully unsupervised approach to improving word-in-context (WiC) representations in PLMs, achieved via a simple and efficient WiC-targeted fine-tuning procedure: MirrorWiC. The proposed method leverages only raw texts sampled from Wikipedia, assuming no sense-annotated data, and learns context-aware word representations within a standard contrastive learning setup. We experiment with a series of standard and comprehensive WiC benchmarks across multiple languages. Our proposed fully unsupervised MirrorWiC models obtain substantial gains over off-the-shelf PLMs across all monolingual, multilingual and cross-lingual setups. Moreover, on some standard WiC benchmarks, MirrorWiC is even on-par with supervised models fine-tuned with in-task data and sense labels.

MirrorWiC: On Eliciting Word-in-Context Representations from Pretrained Language Models

What is the first word that comes to your mind when you hear “giraffe” or “damsel” or “freedom”? Such free associations contain a huge amount of information on the mental representations of the corresponding concepts, and are thus an extremely valuable testbed for the evaluation of semantic representations extracted from corpora. In this paper, we present FAST (Free ASsociation Tasks), a free association dataset for English rigorously sampled from two standard free association norms (the Edinburgh Associative Thesaurus and the University of South Florida Free Association Norms), discuss two evaluation tasks, and provide baseline results. In parallel, we discuss methodological considerations concerning the desiderata for a proper evaluation of semantic representations.

FAST: A carefully sampled and cognitively motivated dataset for distributional semantic evaluation

Infusing factual knowledge into pretrained models is fundamental for many knowledge-intensive tasks. In this paper, we propose Mixture-of-Partitions (MoP), an infusion approach that can handle a very large knowledge graph (KG) by partitioning it into smaller sub-graphs and infusing their specific knowledge into various BERT models using lightweight adapters. To leverage the overall factual knowledge for a target task, these sub-graph adapters are further fine-tuned along with the underlying BERT through a mixture layer. We evaluate our MoP with three biomedical BERTs (SciBERT, BioBERT, PubmedBERT) on six downstream tasks (inc. NLI, QA, Classification), and the results show that our MoP consistently enhances the underlying BERTs in task performance, and achieves new SOTA performances on five evaluated datasets.

Downloads

Next from EMNLP 2021

CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Similar lecture

Probing Pre-trained Language Models for Semantic Attributes and their Values

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from EMNLP 2021

CLIPScore: A Reference-free Evaluation Metric for Image Captioning

Similar lecture

Probing Pre-trained Language Models for Semantic Attributes and their Values

Downloads