United States

Readers of academic research papers often read with the goal of answering specific questions. Question Answering systems that can answer those questions can make consumption of the content much more efficient. However, building such tools requires data that reflect the difficulty of the task arising from complex reasoning about claims made in multiple parts of a paper. In contrast, existing information-seeking question answering datasets usually contain questions about generic factoid-type information. We therefore present QASPER, a dataset of 5,049 questions over 1,585 Natural Language Processing papers. Each question is written by an NLP practitioner who read only the title and abstract of the corresponding paper, and the question seeks information present in the full text. The questions are then answered by a separate set of NLP practitioners who also provide supporting evidence to answers. We find that existing models that do well on other QA tasks do not perform well on answering these questions, underperforming humans by at least 27 F1 points when answering them from entire papers, motivating further research in document grounded, information-seeking QA, which our dataset is designed to facilitate.

NAACL 2021

A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers

2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics.

**Whova App** 
Stay in touch with your fellow conference attendees via the [Whova App](https://whova.com/portal/webapp/nacon_202106/)

**Conference Structure**
https://2021.naacl.org/blog/conference-structure/

**Walkthrough video of how to NAACL 2021** 

Please take a moment to view this video explaining how to navigate the platform, attend sessions network with other attendees. 


<figure class="video_container">
  <iframe src="https://screencast-o-matic.com/watch/crhwbGVh3vx?v=6&ff=1&title=0&controls=1" width=640  height=350  frameborder="0" allowfullscreen="true"> </iframe>
</figure>

<br>
<br>

technical paper

We investigate grounded language learning through real-world data, by modelling a teacher-learner dynamics through the natural interactions occurring between users and search engines; in particular, we explore the emergence of semantic generalization from unsupervised dense representations outside of synthetic environments. A grounding domain, a denotation function and a composition function are learned from user data only. We show how the resulting semantics for noun phrases exhibits compositional properties while being fully learnable without any explicit labelling. We benchmark our grounded semantics on compositionality and zero-shot inference tasks, and we show that it provides better results and better generalizations than SOTA non-grounded models, such as word2vec and BERT.

Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction

While neural networks produce state-of-the-art performance in several NLP tasks, they generally depend heavily on lexicalized information, which transfer poorly between domains. We present a combination of two strategies to mitigate this dependence on lexicalized information in fact verification tasks. We present a data distillation technique for delexicalization, which we then combine with a model distillation method to prevent aggressive data distillation. We show that by using our solution, not only does the performance of an existing state-of-the-art model remain at par with that of the model trained on a fully lexicalized data, but it also performs better than it when tested out of domain. We show that the technique we present encourages models to extract transferable facts from a given fact verification dataset.

Data and Model Distillation as a Solution for Domain-transferable Fact Verification

Coreference resolution is an important component in analyzing narrative text from administrative data (e.g., clinical or police sources).

Adapting Coreference Resolution for Processing Violent Death Narratives

In human-level NLP tasks, such as predicting mental health, personality, or demographics, the number of observations is often smaller than the standard 768+ hidden state sizes of each layer within modern transformer-based language models, limiting the ability to effectively leverage transformers. Here, we provide a systematic study on the role of dimension reduction methods (principal components analysis, factorization techniques, or multi-layer auto-encoders) as well as the dimensionality of embedding vectors and sample sizes as a function of predictive performance. We first find that fine-tuning large models with a limited amount of data pose a significant difficulty which can be overcome with a pre-trained dimension reduction regime. RoBERTa consistently achieves top performance in human-level tasks, with PCA giving benefit over other reduction methods in better handling users that write longer texts. Finally, we observe that a majority of the tasks achieve results comparable to the best performance with just 1/12 of the embedding dimension.

Empirical Evaluation of Pre-trained Transformers for Human-Level NLP: The Role of Sample Size and Dimensionality

The COVID-19 pandemic has spawned a diverse body of scientific literature that is challenging to navigate, stimulating interest in automated tools to help find useful knowledge. We pursue the construction of a knowledge base (KB) of mechanisms -- a fundamental concept across the sciences, which encompasses activities, functions and causal relations, ranging from cellular processes to economic impacts. We extract this information from the natural language of scientific papers by developing a broad, unified schema that strikes a balance between relevance and breadth. We annotate a dataset of mechanisms with our schema and train a model to extract mechanism relations from papers. Our experiments demonstrate the utility of our KB in supporting interdisciplinary scientific search over COVID-19 literature, outperforming the prominent PubMed search in a study with clinical experts. Our search engine, dataset and code are publicly available at https://covidmechanisms.apps.allenai.org/ .

Extracting a Knowledge Base of Mechanisms from COVID-19 Papers

In this paper, we study the importance of context in predicting the citation worthiness of sentences in scholarly articles. We formulate this problem as a sequence labeling task solved using a hierarchical BiLSTM model. We contribute a new benchmark dataset containing over two million sentences and their corresponding labels. We preserve the sentence order in this dataset and perform document-level train/test splits, which importantly allows incorporating contextual information in the modeling process. We evaluate the proposed approach on three benchmark datasets. Our results quantify the benefits of using context and contextual embeddings for citation worthiness. Lastly, through error analysis, we provide insights into cases where context plays an essential role in predicting citation worthiness.

On the Use of Context for Predicting Citation Worthiness of Sentences in Scholarly Articles

Tracking entities throughout a procedure described in a text is challenging due to the dynamic nature of the world described in the process. Firstly, we propose to formulate this task as a question answering problem. This enables us to use pre-trained transformer-based language models on other QA benchmarks by adapting those to the procedural text understanding. Secondly, since the transformer-based language models cannot encode the flow of events by themselves, we propose a Time-Stamped Language Model(TSLM) to encode event information in LMs architecture by introducing the timestamp encoding. Our model evaluated on the Propara dataset shows improvements on the published state-of-the-art results with a 3.1\% increase in F1 score. Moreover, our model yields better results on the location prediction task on the NPN-Cooking dataset. This result indicates that our approach is effective for procedural text understanding in general.

Time-Stamped Language Model: Teaching Language Models to Understand The Flow of Events

Multi-hop reasoning requires aggregation and inference from multiple facts. To retrieve such facts, we propose a simple approach that retrieves and reranks set of evidence facts jointly. Our approach first generates unsuper- vised clusters of sentences as candidate evi- dence by accounting links between sentences and coverage with the given query. Then, a RoBERTa-based reranker is trained to bring the most representative evidence cluster to the top. We specifically emphasize on the impor- tance of retrieving evidence jointly by showing several comparative analyses to other meth- ods that retrieve and rerank evidence sen- tences individually. First, we introduce sev- eral attention- and embedding-based analy- ses, which indicate that jointly retrieving and reranking approaches can learn compositional knowledge required for multi-hop reasoning. Second, our experiments show that jointly re- trieving candidate evidence leads to substan- tially higher evidence retrieval performance when fed to the same supervised reranker. In particular, our joint retrieval and then rerank- ing approach achieves new state-of-the-art evi- dence retrieval performance on two multi-hop question answering (QA) datasets: 30.5 Re- call@2 on QASC, and 67.6% F1 on MultiRC. When the evidence text from our joint retrieval approach is fed to a RoBERTa-based answer selection classifier, we achieve new state-of- the-art QA performance on MultiRC and sec- ond best result on QASC.

If You Want to Go Far Go Together: Unsupervised Joint Candidate Evidence Retrieval for Multi-hop Question Answering

This paper proposes a question-answering (QA) benchmark for spatial reasoning on natural language text which contains more realistic spatial phenomena not covered by prior work and is challenging for state-of-the-art language models (LM). We propose a distant supervision method to improve on this task. Specifically, we design grammar and reasoning rules to automatically generate a spatial description of visual scenes and corresponding QA pairs. Experiments show that further pretraining LMs on these automatically generated data significantly improves LMs' capability on spatial understanding, which in turn helps to better solve two external datasets, bAbI, and boolQ. We hope that this work can foster investigations into more sophisticated models for spatial reasoning over text.

SPARTQA: A Textual Question Answering Benchmark for Spatial Reasoning

Complex question answering often requires finding a reasoning chain that consists of multiple evidence pieces. Current approaches incorporate the strengths of structured knowledge and unstructured text, assuming text corpora is semi-structured. Building on dense retrieval methods, we propose a new multi-step retrieval approach (BeamDR) that iteratively forms an evidence chain through beam search in dense representations. When evaluated on multi-hop question answering, BeamDR is competitive to state-of-the-art systems, without using any semi-structured information. Through query composition in dense space, BeamDR captures the implicit relationships between evidence in the reasoning chain.

A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers

Downloads

Next from NAACL 2021

Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction

Similar lecture

Linguistic Complexity Loss in Text-Based Therapy

A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers

.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 NAACL 2021

Language in a (Search) Box: Grounding Language Learning in Real-World Human-Machine Interaction

Similar lecture

Linguistic Complexity Loss in Text-Based Therapy

Downloads