Thailand

This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning. One way to robustify these models is by supervising to not only answer right, but also with right reasoning chains. An existing direction is to annotate reasoning chains to train models, requiring expensive additional annotations. In contrast, we propose a new approach to learn evidentiality, deciding whether the answer prediction is supported by correct evidences, without such annotations. Instead, we compare counterfactual changes in answer confidence with and without evidence sentences, to generate &quot;pseudo-evidentiality&quot; annotations. We validate our proposed model on an original set and challenge set in HotpotQA, showing that our method is accurate and robust in multi-hop reasoning.

IJCNLP-AACL 2021

Robustifying Multi-hop QA through Pseudo-Evidentiality Training

evidentiality training

reasoning shortcut

multi-hop qa

**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).

This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning. One way to robustify these models is by supervising to not only answer right, but also with right reasoning chains. An existing direction is to annotate reasoning chains to train models, requiring expensive additional annotations. In contrast, we propose a new approach to learn evidentiality, deciding whether the answer prediction is supported by correct evidences, without such annotations. Instead, we compare counterfactual changes in answer confidence with and without evidence sentences, to generate "pseudo-evidentiality" annotations. We validate our proposed model on an original set and challenge set in HotpotQA, showing that our method is accurate and robust in multi-hop reasoning.

poster

Professional summaries are written with document-level information, such as the theme of the document, in mind. This is in contrast with most seq2seq decoders which simultaneously learn to focus on salient content, while deciding what to generate, at each decoding step. With the motivation to narrow this gap, we introduce Focus Attention Mechanism, a simple yet effective method to encourage decoders to proactively generate tokens that are similar or topical to the input document. Further, we propose a Focus Sampling method to enable generation of diverse summaries, an area currently understudied in summarization. When evaluated on the BBC extreme summarization task, two state-of-the-art models augmented with Focus Attention generate summaries that are closer to the target and more faithful to their input documents, outperforming their vanilla counterparts on ROUGE and multiple faithfulness measures. We also empirically demonstrate that Focus Sampling is more effective in generating diverse and faithful summaries than top-k or nucleus sampling-based decoding methods.

Focus Attention: Promoting Faithfulness and Diversity in Summarization

The availability of large-scale datasets has driven the development of neural models that create generic summaries from single or multiple documents. In this work we consider query focused summarization (QFS), a task for which training data in the form of queries, documents, and summaries is not readily available. We propose to decompose QFS into (1) query modeling (i.e., finding supportive evidence within a set of documents for a query) and (2) conditional language modeling (i.e., summary generation). We introduce MaRGE, a Masked ROUGE Regression framework for evidence estimation and ranking which relies on a unified representation for summaries and queries, so that summaries in generic data can be converted into proxy queries for learning a query model. Experiments across QFS benchmarks and query types show that our model achieves state-of-the-art performance despite learning from weak supervision.

Generating Query Focused Summaries from Query-Free Resources

In news articles the lead bias is a common phenomenon that usually dominates the learning signals for neural extractive summarizers, severely limiting their performance on data with different or even no bias. In this paper, we introduce a novel technique to demote lead bias and make the summarizer focus more on the content semantics. Experiments on two news corpora with different degrees of lead bias show that our method can effectively demote the model's learned lead bias and improve its generality on out-of-distribution data, with little to no performance loss on in-distribution data.

Demoting the Lead Bias in News Summarization via Alternating Adversarial Learning

Machine reading comprehension (MRC) is a crucial task in natural language processing and has achieved remarkable advancements. However, most of the neural MRC models are still far from robust and fail to generalize well in real-world applications. In order to comprehensively verify the robustness and generalization of MRC models, we introduce a real-world Chinese dataset -- DuReader_robust . It is designed to evaluate the MRC models from three aspects: over-sensitivity, over-stability and generalization. Comparing to previous work, the instances in DuReader_robust are natural texts, rather than the altered unnatural texts. It presents the challenges when applying MRC models to real-world applications. The experimental results show that MRC models do not perform well on the challenge test set. Moreover, we analyze the behavior of existing models on the challenge test set, which may provide suggestions for future model development. The dataset and codes are publicly available at https://github.com/baidu/DuReader.

DuReader_robust: A Chinese Dataset Towards Evaluating Robustness and Generalization of Machine Reading Comprehension in Real-World Applications

With the recent advancements in deep learning, neural solvers have gained promising results in solving math word problems. However, these SOTA solvers only generate binary expression trees that contain basic arithmetic operators and do not explicitly use the math formulas. As a result, the expression trees they produce are lengthy and uninterpretable because they need to use multiple operators and constants to
represent one single formula. In this paper, we propose sequence-to-general tree (S2G) that
learns to generate interpretable and executable operation trees where the nodes can be formulas with an arbitrary number of arguments. With nodes now allowed to be formulas, S2G can learn to incorporate mathematical domain knowledge into problem-solving, making the results more interpretable. Experiments show that S2G can achieve a better performance against strong baselines on problems that require domain knowledge.

Sequence to General Tree: Knowledge-Guided Geometry Word Problem Solving

MeasEval aims at identifying quantities along with the entities that are measured with additional properties within English scientific documents. The variety of styles used makes measurements, a most crucial aspect of scientific writing, challenging to extract. This paper presents ablation studies making the case for several preprocessing steps such as specialized tokenization rules. For linguistic structure, we encode dependency trees in a Deep Graph Convolution Network (DGCNN) for multi-task classification.

CLaC-np at SemEval-2021 Task 8: Dependency DGCNN

We developed a system to generate structured representations of research contributions described in NLP publications, achieving the top performance in the NCG shared task. We combined a cascade of neural models with rule-based methods. In particular, we proposed a novel approach for triple extraction, where we extracted triples with different characteristics using different relation classification methods.

UIUC_BioNLP at SemEval-2021 Task 11: A Cascade of Neural Models for Structuring Scholarly NLP Contributions

This paper describes the system submitted to SemEval 2021 Task 5: Toxic Spans Detection. The task concerns evaluating systems that detect the spans that make a text toxic when detecting such spans are possible. To address the possibly multi-span detection problem, we develop a start-to-end tagging framework on the top of RoBERTa based language model. Besides, we design a custom loss function which take distance into account. In comparison to other participating teams, our system
has achieved 69.03% F1 score, which is slight lower (-1.8 and -1.73) than the top 1
(70.83%) and top 2 (70.77%), respectively.

MedAI at SemEval-2021 Task 5: Start-to-end Tagging Framework for Toxic Spans Detection

This poster describes the Duluth system that participated in SemEval-2021 Task 11, NLP Contribution Graph. It shows the process of extracting contribution sentences and scientific entities and relations from scholarly articles in the domain of Natural Language Processing. Our solution uses DeBERTa for multi-class sentence classification to extract the contributing sentences and their information unit, and dependency parsing to extract phrases from each sentence and format into subject-predicate-object triples.

Duluth at SemEval-2021 Task 11: Applying DeBERTa to Contributing Sentence Selection and Dependency Parsing for Entity Extraction

This work presents our contribution to SemEval-2021 Task 2: Multilingual and Cross-lingual Word-in-Context Disambiguation (MCL-WiC). Our experiments cover English (EN-EN) sub-track from the multilingual setting of the task. We experiment with several pre-trained language models and investigate an impact of different top-layers on fine-tuning. We find the combination of Cosine Similarity and ReLU activation leading to the most effective fine-tuning procedure. Our best model results in accuracy 92.7%, which is the fourth-best score in EN-EN sub-track.

Robustifying Multi-hop QA through Pseudo-Evidentiality Training

Downloads

Next from IJCNLP-AACL 2021

Focus Attention: Promoting Faithfulness and Diversity in Summarization

Similar lecture

Weakly Supervised Pre-Training for Multi-Hop Retriever