United States

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>

NAACL 2021

Pre-trained language models have achieved huge success on a wide range of NLP tasks. However, contextual representations from pre-trained models contain entangled semantic and syntactic information, and therefore cannot be directly used to derive useful semantic sentence embeddings for some tasks. Paraphrase pairs offer an effective way of learning the distinction between semantics and syntax, as they naturally share semantics and often vary in syntax. In this work, we present ParaBART, a semantic sentence embedding model that learns to disentangle semantics and syntax in sentence embeddings obtained by pre-trained language models. ParaBART is trained to perform syntax-guided paraphrasing, based on a source sentence that shares semantics with the target paraphrase, and a parse tree that specifies the target syntax. In this way, ParaBART learns disentangled semantic and syntactic representations from their respective inputs with separate encoders. Experiments in English show that ParaBART outperforms state-of-the-art sentence embedding models on unsupervised semantic similarity tasks. Additionally, we show that our approach can effectively remove syntactic information from semantic sentence embeddings, leading to better robustness against syntactic variation on downstream semantic tasks.

Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models

technical paper

Explainable Multi-hop Verbal Reasoning Through Internal Monologue

RECONSIDER: Improved Re-Ranking using Span-Focused Cross-Attention for Open Domain Question Answering

Robust Question Answering Through Sub-part Alignment

Text Modular Networks: Learning to Decompose Tasks in the Language of Existing Models

Self-Supervised Test-Time Learning for Reading Comprehension

Capturing Row and Column Semantics in Transformer Based Question Answering over Tables

DuoRAT: Towards Simpler Text-to-SQL Models

Understanding by Understanding Not: Modeling Negation in Language Models

Looking Beyond Sentence-Level Natural Language Inference for Question Answering and Text Summarization

Structure-Grounded Pretraining for Text-to-SQL

https://assets.underline.io/transcript/13574/subtitle/354286b41241bc886e9f7c74ae6178ba.vtt

English (automatic)

Disentangling Semantics and Syntax in Sentence Embeddings with Pre-trained Language Models

Downloads

Next from NAACL 2021

Explainable Multi-hop Verbal Reasoning Through Internal Monologue

Similar lecture

FUDGE: Controlled Text Generation With Future Discriminators