United States

Conversational Question Answering (ConvQA) is required to answer the current question, conditioned on the observable paragraph-level context and conversation history. Previous works have intensively studied history-dependent reasoning. 
They perceive and absorb topic-related information of prior utterances in the interactive encoding stage. It yielded significant improvement compared to history-independent reasoning. This paper further strengthens the ConvQA encoder by establishing long-distance dependency among global utterances in multi-turn conversation. We use multi-layer transformers to resolve long-distance relationships, which potentially contribute to the reweighting of attentive information in historical utterances.
Experiments on QuAC show that our method obtains a substantial improvement (1%), yielding the F1 score of 73.7%. All source codes are available at https://github.com/jaytsien/GHR.

NAACL 2022

Capturing Conversational Interaction for Question Answering via Global History Reasoning

global history reasoning

conversational qa

machine reading comprehension

## 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

poster

Commonsense reasoning in natural language is a desired ability of artificial intelligent systems. 
For solving complex commonsense reasoning tasks, a typical solution is to enhance pre-trained language models~(PTMs) with a knowledge-aware graph neural network~(GNN) encoder that models a commonsense knowledge graph~(CSKG).
Despite the effectiveness, these approaches are built on heavy architectures, and can't clearly explain how external knowledge resources improve the reasoning capacity of PTMs. 
Considering this issue, we conduct a deep empirical analysis, and find that it is indeed \emphrelation features from CSKGs (but not \emphnode features) that mainly contribute to the performance improvement of PTMs. 
Based on this finding, we design a simple MLP-based knowledge encoder that utilizes statistical relation paths as features. 
Extensive experiments conducted on five benchmarks demonstrate the effectiveness of our approach, which also largely reduces the parameters for encoding CSKGs.
Our codes and data are publicly available at~\urlhttps://github.com/RUCAIBox/SAFE.

$Great~Truths~are ~Always ~Simple:$ A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models

Question matching is the task of identifying whether two questions have the same intent. For better reasoning the relationship between questions, existing studies adopt multiple interaction modules and perform multi-round reasoning via deep neural networks. In this process, there are two kinds of critical information that are commonly employed: the representation information of original questions and the interactive information between pairs of questions. However, previous studies tend to transmit only one kind of information, while failing to utilize both kinds of information simultaneously. To address this problem, in this paper, we propose a Full Information Transmission Network (FITN) that can transmit both representation and interactive information together in a simultaneous fashion. More specifically, we employ a novel memory-based attention for keeping and transmitting the interactive information through a global interaction matrix. Besides, we apply an original-average mixed connection method to effectively transmit the representation information between different reasoning rounds, which helps to preserve the original representation features of questions along with the historical hidden features. Experiments on two standard benchmarks demonstrate that our approach outperforms strong baseline models.

All Information is Valuable: Question Matching over Full Information Transmission Network

Machine Reading Comprehension with Unanswerable Questions is a difficult NLP task, challenged by the questions which can not be answered from passages.
It is observed that subtle literal changes often make an answerable question unanswerable, however, most MRC models fail to recognize such changes.
To address this problem, in this paper, we propose a span-based method of Contrastive Learning (spanCL) which explicitly contrast answerable questions with their answerable and unanswerable counterparts at the answer span level.
With spanCL, MRC models are forced to perceive crucial semantic changes from slight literal differences.
Experiments on SQuAD 2.0 dataset show that spanCL can improve baselines significantly, yielding 0.86\textasciitilde 2.14 absolute EM improvements. 
Additional experiments also show that spanCL is an effective  way to utilize generated questions.  

To Answer or Not To Answer? Improving Machine Reading Comprehension Model with  Span-based Contrastive Learning

Given a context knowledge base (KB) and a corresponding question, the Knowledge Base Question Answering task aims to retrieve correct answer entities from this KB. Despite sophisticated retrieval algorithms, the impact of the low-resource (incomplete) KB is not fully exploited, where contributing components (\ie. key entities and/or relations) may be absent for question answering. To effectively address this problem, we propose a contrastive regularization based method, which is motivated by the \textttlearn-\textttby-\textttanalogy capability from human readers.
Specifically, the proposed work includes two major modules: the knowledge extension and sMoCo module. The former aims at exploiting the latent knowledge from the context KB and generating auxiliary information in the form of question-answer pairs. The later module utilizes those additional pairs and applies the contrastive regularization to learn informative representations, that making \texttthard positive pairs attracted and \texttthard negative pairs separated. Empirically, we achieved the state-of-the-art performance on the WebQuestionsSP dataset and the effectiveness of proposed modules is also evaluated.

Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering

Compared with unimodal data, multimodal data can provide more features to help the model analyze the sentiment of data. Previous research works rarely consider token-level feature fusion, and few works explore learning the common features related to sentiment in multimodal data to help the model fuse multimodal features. In this paper, we propose a Contrastive Learning and Multi-Layer Fusion (CLMLF) method for multimodal sentiment detection. Specifically, we first encode text and image to obtain hidden representations, and then use a multi-layer fusion module to align and fuse the token-level features of text and image. In addition to the sentiment analysis task, we also designed two contrastive learning tasks, label based contrastive learning and data based contrastive learning tasks, which will help the model learn common features related to sentiment in multimodal data. Extensive experiments conducted on three publicly available multimodal datasets demonstrate the effectiveness of our approach for multimodal sentiment detection compared with existing methods. The codes are available for use at https: //github.com/Link-Li/CLMLF

CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection

Sarcasm employs ambivalence, where one says something positive but actually means negative, and vice versa. The essence of sarcasm, which is also a sufficient and necessary condition, is the conflict between literal and implied sentiments expressed in one sentence. However, it is difficult to recognize such sentiment conflict because the sentiments are mixed or even implicit. As a result, the recognition of sophisticated and obscure sentiment brings in a great challenge to sarcasm detection. In this paper, we propose a Dual-Channel Framework by modeling both literal and implied sentiments separately. Based on this dual-channel framework, we design the Dual-Channel Network~(DC-Net) to recognize sentiment conflict. Experiments on political debates (i.e. IAC-V1 and IAC-V2) and Twitter datasets show that our proposed DC-Net achieves state-of-the-art performance on sarcasm recognition. Our code is released to support research.

A Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict

Linguistic bias in Deep Neural Network (DNN) based Natural Language Processing (NLP) systems is a critical problem that needs attention. The problem further intensifies in the case of security systems, such as speaker verification, where fairness is essential. Speaker verification systems are intelligent systems that determine if two speech recordings belong to the same speaker. Such human-oriented security systems should be usable by diverse people speaking varied languages. Thus, a speaker verification system trained on speech in one language should generalize when tested for other languages. However, DNN-based models are often language-dependent. Previous works explore domain adaptation to fine-tune the pre-trained model for out-of-domain languages. Fine-tuning the model individually for each existing language is expensive. Hence, it limits the usability of the system. This paper proposes the cost-effective idea of integrating a lightweight embedding with existing speaker verification systems to mitigate linguistic bias without adaptation. This work is motivated by the theoretical hypothesis that attentive-frames could help generate language-agnostic embeddings. For scientific validation of this hypothesis, we propose two frame-attentive networks and investigate the effect of their integration with baselines for twelve languages. Empirical results suggest that frame-attentive embedding can cost-effectively reduce linguistic bias and enhance the usability of baselines.  

FAtNet: Cost-Effective Approach Towards Mitigating the Linguistic Bias in Speaker Verification Systems

Adversarial attack of structured prediction models faces various challenges such as the difficulty of perturbing discrete words, the sentence quality issue, and the sensitivity of outputs to small perturbations. In this work, we introduce SHARP, a new attack method that formulates the black-box adversarial attack as a search-based optimization problem with a specially designed objective function considering sentence fluency, meaning preservation and attacking effectiveness. Additionally, three different searching strategies are analyzed and compared, i.e., Beam Search, Metropolis-Hastings Sampling, and Hybrid Search. We demonstrate the effectiveness of our attacking strategies on two challenging structured prediction tasks: Pos-tagging and dependency parsing. Through automatic and human evaluations, we show that our method performs a more potent attack compared with pioneer arts. Moreover, the generated adversarial examples can be used to successfully boost the robustness and performance of the victim model via adversarial training.

SHARP: Search-Based Adversarial Attack for Structured Prediction

The Penn-Helsinki Parsed Corpus of Early Modern English (PPCEME), a 1.7-million-word treebank that is an important resource for research in syntactic change, has several properties that present potential challenges for NLP technologies. We describe these  key features of PPCEME that make it challenging for parsing, including a larger and more varied set of function tags than in the Penn Treebank, and present results for this corpus using a modified version of the Berkeley Neural Parser and the approach to function tag recovery of Gabbard et al. (2006).  While this approach to function tag recovery gives reasonable results, it is in some ways inappropriate for span-based parsers.   We also present further evidence of the importance of in-domain pretraining for contextualized word representations.  The resulting parser will be used to parse Early English Books Online, a 1.5 billion word corpus whose utility for the study of syntactic change will be greatly increased with the addition of accurate parse trees.
 

Capturing Conversational Interaction for Question Answering via Global History Reasoning

Downloads

Next from NAACL 2022

$Great~Truths~are ~Always ~Simple:$ A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models

Similar lecture

Continual Machine Reading Comprehension via Uncertainty-aware Fixed Memory and Adversarial Domain Adaptation