Thailand

There are two major classes of natural language grammars --- the dependency grammar that models one-to-one correspondences between words and the constituency grammar that models the assembly of one or several corresponded words. While previous unsupervised parsing methods mostly focus on only inducing one class of grammars, we introduce a novel model, StructFormer, that can induce dependency and constituency structure at the same time. To achieve this, we propose a new parsing framework that can jointly generate a constituency tree and dependency graph. Then we integrate the induced dependency relations into the transformer, in a differentiable manner, through a novel dependency-constrained self-attention mechanism. Experimental results show that our model can achieve strong results on unsupervised constituency parsing, unsupervised dependency parsing, and masked language modeling at the same time.

ACL 2021

StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling

unsupervised constituency parsing

unsupervised dependency parser

masked language model

**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). 

This Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) was to be held in Bangkok, Thailand, during August 1-6, 2021 and is now virtual on the Underline platform.

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

technical paper

We propose a transition-based bubble parser to perform coordination structure identiﬁcation and dependency-based syntactic analysis simultaneously. Bubble representations were proposed in the formal linguistics literature decades ago; they enhance dependency trees by encoding coordination boundaries and internal relationships within coordination structures explicitly. In this paper, we introduce a transition system and neural models for parsing these bubble-enhanced structures. Experimental results on the English Penn Treebank and the English GENIA corpus show that our parsers beat previous state-of-the-art approaches on the task of coordination structure prediction, especially for the subset of sentences with complex coordination structures.

Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction

Recent years have seen the paradigm shift of Named Entity Recognition (NER) systems from sequence labeling to span prediction. Despite its preliminary effectiveness, the span prediction model's architectural bias has not been fully understood. In this paper, we first investigate the strengths and weaknesses when the span prediction model is used for named entity recognition compared with the sequence labeling framework and how to further improve it, which motivates us to make complementary advantages of systems based on different paradigms. We then reveal that span prediction, simultaneously, can serve as a system combiner to re-recognize named entities from different systems' outputs. We experimentally implement 154 systems on 11 datasets, covering three languages, comprehensive results show the effectiveness of span prediction models that both serve as base NER systems and system combiners. We make all codes and datasets available: \url{https://github.com/neulab/spanner}, as well as an online system demo: \url{http://spanner.sh}. Our model also has been deployed into the ExplainaBoard platform, which allows users to flexibly perform a system combination of top-scoring systems in an interactive way: \url{http://explainaboard.nlpedia.ai/leaderboard/task-ner/}.

SpanNER: Named Entity Re-/Recognition as Span Prediction

Strong Equivalence of TAG and CCG

End-to-End task-oriented dialogue systems generate responses based on dialog history and an accompanying knowledge base (KB). Inferring those KB entities that are most relevant for an utterance is crucial for response generation. Existing state of the art scales to large KBs by softly filtering over irrelevant KB information. In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record. and, (2) an auxiliary loss that helps in separating contextually unrelated KB information. We also propose a new metric -- multiset entity F1 which fixes a correctness issue in the existing entity F1 metric. Experimental results on three publicly available task-oriented dialog datasets show that our proposed approach outperforms existing state-of-the-art models.

Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs

Proposal of large-scale datasets has facilitated research on deep neural models for news summarization. 
Deep learning can also be potentially useful for spoken dialogue summarization, which can benefit a range of real-life scenarios including customer service management and medication tracking. 
To this end, we propose DialogSum, a large-scale labeled dialogue summarization dataset. 
We conduct empirical analysis on DialogSum using state-of-the-art neural summarizers. 
Experimental results show unique challenges in dialogue summarization, such as spoken terms, special discourse structures, coreferences and ellipsis, pragmatics and social common sense, which require specific representation learning technologies to better deal with.

Dialog{S}um: {A} Real-Life Scenario Dialogue Summarization Dataset

The growing ecosystem of data sharing in science has put dataset search into the focus. To make data sharing and reuse more feasible, new retrieval tools and services are being developed. Currently, dataset retrieval relies almost exclusively on metadata provided by the publishers. To extend this knowledge source our work studies the task of ``dataset review mining'' in scientific publications. For the field of Natural Language Processing we collect metadata about datasets from established resources such as the ELRA and LDC catalogs, and then extract review statements about the datasets from ACL Anthology Corpus publications, compiling the Webis-Dataset-Reviews-21 corpus. By analyzing the reviews we identify different categories of what paper authors write about data. To the best of our knowledge, this is the first analysis of this kind in the field of Natural Language Processing, albeit similar analyses have been carried out in the social and medical sciences. Our corpus and the underlying code are shared alongside this paper.

Beyond Metadata: What Paper Authors Say About Corpora They Use

There have been several attempts to create an accurate and thorough emotion lexicon in English, which identifies the emotional content of words. Of the several commonly used resources, the NRC emotion lexicon has received the most attention due to its availability, size, and its choice of Plutchik's expressive 8-class emotion model. In this paper we identify a large number of troubling entries in the NRC lexicon, where words that should in most contexts be emotionally neutral, with no affect (e.g., lesbian, stone, mountain), are associated with emotional labels that are inaccurate, nonsensical, pejorative, or, at best, highly contingent and context-dependent (e.g., lesbian labeled as disgust and sadness, stone as anger, or mountain as anticipation). We describe a procedure for semi-automatically correcting these problems in the NRC, which includes disambiguating POS categories and aligning NRC entries with other emotion lexicons to infer the accuracy of labels. We demonstrate via an experimental benchmark that the quality of the resources is thus improved. We release the revised resource and our code to enable other researchers to reproduce and build upon results.

Hell Hath No Fury? Correcting Bias in the NRC Emotion Lexicon

Language provides speakers with a rich system of modality for expressing thoughts about events, without being committed to their actual occurrence. Modality is commonly used in the political news domain, where both actual and possible courses of events are discussed. NLP systems struggle with these semantic phenomena, often incorrectly extracting events which did not happen, which can lead to issues in downstream applications. We present an open-domain, lexicon-based event extraction system that captures various types of modality. This information is valuable for Question Answering, Knowledge Graph construction and Fact-checking tasks, and our evaluation shows that the system is sufficiently strong to be used in downstream applications.

Modality and Negation in Event Extraction

Incidents in industries have huge social and political impact and minimizing the consequent damage has been a high priority. However, automated analysis of repositories of incident reports has remained a challenge. In this paper, we focus on automatically extracting events from incident reports. Due to absence of event annotated datasets for industrial incidents we employ a transfer learning based approach which is shown to outperform several baselines. We further provide detailed analysis regarding effect of increase in pre-training data and provide explainability of why pre-training improves the performance.

Extracting Events from Industrial Incident Reports

We apply statistical techniques from natural language processing to a collection of Western and Hong Kong–based English-language newspaper articles spanning the years 1998–2020, studying the difference and evolution of its portrayal. We observe that both content and attitudes differ between Western and Hong Kong–based sources. 
ANOVA on keyword frequencies reveals that Hong Kong–based papers discuss protests and democracy less often.
Topic modeling detects salient aspects of protests and shows that Hong Kong–based papers made fewer references to police violence during the Anti-Extradition Law Amendment Bill Movement.
Diachronic shifts in word embedding neighborhoods reveal a shift in the characterization of salient keywords once the Movement emerged.
Together, these raise questions about the existence of anodyne reporting from Hong Kong–based media.
Likewise, they illustrate the importance of sample selection for protest event analysis.

StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling

Downloads

Next from ACL 2021

Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction

Similar lecture

Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

StructFormer: Joint Unsupervised Induction of Dependency and Constituency Structure from Masked Language Modeling

.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 ACL 2021

Transition-based Bubble Parsing: Improvements on Coordination Structure Prediction

Similar lecture

Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads