Thailand

Existing NLU models have been shown to incorporate dataset biases leading to strong performance on in-distribution test sets but poor performance on out-of-distribution (OOD) ones. We introduce a simple yet effective debiasing framework whereby the shallow representations of the main model are used to derive a bias model and both models are trained simultaneously. During training, the bias model is used to down-weight biased samples for the main model and participates in de-emphasizing its biased representations. Conversely, the main model down-weights the unbiased samples for the bias model. We demonstrate on three well studied NLU tasks that despite its simplicity, our method leads to competitive OOD results. It significantly outperforms other debiasing approaches on two tasks, while still delivering high in-distribution performance.

IJCNLP-AACL 2021

End-to-End Self-Debiasing Framework for Robust NLU Training

bias

bert

robustness

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

technical paper

For natural language processing systems, two kinds of evidence support the use of text representations from neural language models "pretrained" on large unannotated corpora: performance on application-inspired benchmarks (Peters et al., 2018, inter alia), and the emergence of syntactic abstractions in those representations (Tenney et al., 2019, inter alia). On the other hand, the lack of grounded supervision calls into question how well these representations can ever capture meaning (Bender and Koller, 2020). We apply novel probes to recent language models -- specifically focusing on predicate-argument structure as operationalized by semantic dependencies (Ivanova et al., 2012) -- and find that, unlike syntax, semantics is not brought to the surface by today's pretrained models. We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning, yielding benefits to natural language understanding (NLU) tasks in the GLUE benchmark. This approach demonstrates the potential for general-purpose (rather than task-specific) linguistic supervision, above and beyond conventional pretraining and finetuning. Several diagnostics help to localize the benefits of our approach.

Infusing Finetuning with Semantic Dependencies

This work explores a framework for fact verification that leverages pretrained sequence-to-sequence transformer models for sentence selection and label prediction, two key sub-tasks in fact verification. Most notably, improving on previous pointwise aggregation approaches for label prediction, we take advantage of T5 using a listwise approach coupled with data augmentation. With this enhancement, we observe that our label prediction stage is more robust to noise and capable of verifying complex claims by jointly reasoning over multiple pieces of evidence. Experimental results on the FEVER task show that our system attains a FEVER score of 75.87% on the blind test set. This puts our approach atop the competitive FEVER leaderboard at the time of our work, scoring higher than the second place submission by almost two points in label accuracy and over one point in FEVER score.

Exploring Listwise Evidence Reasoning with T5 for Fact Verification

Every natural text is written in some style. Style is formed by a complex combination of different stylistic factors, including formality markers, emotions, metaphors, etc. One cannot form a complete understanding of a text without considering these factors. The factors combine and co-vary in complex ways to form styles. Studying the nature of the covarying combinations sheds light on stylistic language in general, sometimes called cross-style language understanding. This paper provides the benchmark corpus (XSLUE) that
combines existing datasets and collects a new one for sentence-level cross-style language understanding and evaluation. The benchmark contains text in 15 different styles under the proposed four theoretical groupings: figurative, personal, affective, and interpersonal groups. For valid evaluation, we collect an additional diagnostic set by annotating all 15 styles on the same text. Using
XSLUE, we propose three interesting cross-style applications in classification, correlation, and generation. First, our proposed cross-style classifier trained with multiple styles together helps improve overall classification performance against individually-trained style
classifiers. Second, our study shows that some styles are highly dependent on each other in human-written text. Finally, we find that combinations of some contradictive styles likely generate stylistically less appropriate text. We believe our benchmark and case studies help explore interesting future directions for cross-style research. The preprocessed datasets and code are publicly available.

Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding

We introduce DynaSent ('Dynamic Sentiment'), a new English-language benchmark task for ternary (positive/negative/neutral) sentiment analysis. DynaSent combines naturally occurring sentences with sentences created using the open-source Dynabench Platform, which facilities human-and-model-in-the-loop dataset creation. DynaSent has a total of 121,634 sentences, each validated by five crowdworkers, and its development and test splits are designed to produce chance performance for even the best models we have been able to develop; when future models solve this task, we will use them to create DynaSent version 2, continuing the dynamic evolution of this benchmark. Here, we report on the dataset creation effort, focusing on the steps we took to increase quality and reduce artifacts. We also present evidence that DynaSent's Neutral category is more coherent than the comparable category in other benchmarks, and we motivate training models from scratch for each round over successive fine-tuning.

DynaSent: A Dynamic Benchmark for Sentiment Analysis

In this digital age, online users expect personalized content. To cater to diverse group of audiences across online platforms it is necessary to generate multiple variants of same content with differing degree of characteristics (sentiment, style, formality, etc.). Though text-style transfer is a well explored related area, it focuses on flipping the style attribute polarity instead of regulating a fine-grained attribute transfer. In this paper we propose a hierarchical architecture for finer control over the at- tribute, preserving content using attribute dis- entanglement. We demonstrate the effective- ness of the generative process for two different attributes with varied complexity, namely sentiment and formality. With extensive experiments and human evaluation on five real-world datasets, we show that the framework can generate natural looking sentences with finer degree of control of intensity of a given attribute.

A Hierarchical VAE for Calibrating Attributes while Generating Text using Normalizing Flow

Aspect-based Sentiment Analysis (ABSA) aims to identify the aspect terms, their corresponding sentiment polarities, and the opinion terms. There exist seven subtasks in ABSA. Most studies only focus on the subsets of these subtasks, which leads to various complicated ABSA models while hard to solve these subtasks in a unified framework. In this paper, we redefine every subtask target as a sequence mixed by pointer indexes and sentiment class indexes, which converts all ABSA subtasks into a unified generative formulation. Based on the unified formulation, we exploit the pre-training sequence-to-sequence model BART to solve all ABSA subtasks in an end-to-end framework. Extensive experiments on four ABSA datasets for seven subtasks demonstrate that our framework achieves substantial performance gain and provides a real unified end-to-end solution for the whole ABSA subtasks, which could benefit multiple tasks.

A Unified Generative Framework for Aspect-based Sentiment Analysis

While argument mining has achieved significant success in classifying argumentative relations between statements (support, attack, and neutral), we have a limited computational understanding of logical mechanisms that constitute those relations. Most recent studies rely on black-box models, which are not as linguistically insightful as desired. On the other hand, earlier studies use rather simple lexical features, missing logical relations between statements. To overcome these limitations, our work classifies argumentative relations based on four logical and theory-informed mechanisms between two statements, namely (i) factual consistency, (ii) sentiment coherence, (iii) causal relation, and (iv) normative relation. 
We demonstrate that our operationalization of these logical mechanisms classifies argumentative relations without directly training on data labeled with the relations, significantly better than several unsupervised baselines. We further demonstrate that these mechanisms also improve supervised classifiers through representation learning.

Classifying Argumentative Relations Using Logical Mechanisms and Argumentation Schemes

It is well known that human is not good at deception detection because of a natural inclination of truth-bias. However, during a conversation, when an interlocutor (interrogator) is being asked explicitly to assess whether his/her interacting partner (deceiver) is lying, this perceptual judgment depends highly on how the interrogator interprets the context of the conversation. While the deceptive behaviors can be difficult to model due to their heterogeneous manifestation, we hypothesize that this contextual information, i.e., whether the interlocutor trusts or distrusts what his/her partner is saying, provides an important condition in which the deceiver’s deceptive behaviors are more consistently distinct. In this work, we propose a Judgmental-Enhanced Automatic Deception Detection Network (JEADDN) that explicitly considers interrogator’s perceived truths-deceptions with three types of speech-language features (acoustic-prosodic, linguistic, and conversational temporal dynamics features) extracted during a conversation. We evaluate our framework on a large Mandarin Chinese Deception Dialog Database. The results show that the method significantly outperforms the current state-of-the-art approach without conditioning on the judgements of interrogators on this database. We further demonstrate that the behaviors of interrogators are important in detecting deception when the interrogators distrust the deceivers. Finally, with the late fusion of audio, text, and turn-taking dynamics (TTD) features, we obtain promising results of 87.27% and 94.18% accuracy under the conditions that the interrogators trust and distrust the deceivers in deception detection which improves 7.27% and 13.57% than the model without considering the judgements of interlocutor respectively.

``Does it Matter When I Think You Are Lying?" Improving Deception Detection by Integrating Interlocutor's Judgements in Conversations

Many task-oriented dialogue systems use deep reinforcement learning (DRL) to learn policies that respond to the user appropriately and complete the tasks successfully. Training DRL agents with diverse dialogue trajectories prepare them well for rare user requests and unseen situations. One effective diversification method is to let the agent interact with a diverse set of learned user models. However, trajectories created by these artificial user models may contain generation errors, which can quickly propagate into the agent's policy. It is thus important to control the quality of the diversification and resist the noise. In this paper, we propose a novel dialogue diversification method for task-oriented dialogue systems trained in simulators. Our method, Intermittent Short Extension Ensemble (I-SEE), constrains the intensity to interact with an ensemble of diverse user models and effectively controls the quality of the diversification. Evaluations on the Multiwoz dataset show that I-SEE successfully boosts the performance of several state-of-the-art DRL dialogue agents.

High-Quality Dialogue Diversification by Intermittent Short Extension Ensembles

This paper studies the end-to-end construction of an NLP knowledge graph from scientific papers. We focus on extracting four types of relations: evaluatedOn between tasks and datasets, evaluatedBy between tasks and evaluation metrics, as well as coreferent and related relations between the same type of entities. For instance, “F1 score” is coreferent with “F-measure”. We introduce novel methods for each of these relation types and apply our final framework (SciNLP-KG) to 30,000 NLP papers from the ACL Anthology to build a large-scale knowledge graph, which can facilitate automatically constructing scientific leaderboards for the NLP community. The results of our experiments indicate that the resulting knowledge graph contains high-quality information.

End-to-End Self-Debiasing Framework for Robust NLU Training

Downloads

Next from IJCNLP-AACL 2021

Infusing Finetuning with Semantic Dependencies

Similar lecture

Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?

End-to-End Self-Debiasing Framework for Robust NLU Training

.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 IJCNLP-AACL 2021

Infusing Finetuning with Semantic Dependencies

Similar lecture

Out of Order: How important is the sequential order of words in a sentence in Natural Language Understanding tasks?

Downloads