United States

Supervised training with cross-entropy loss implicitly forces models to produce probability distributions that follow a discrete delta distribution. Model predictions in test time are expected to be similar to delta distributions if the classifier determines the class of an input correctly. 
However, the shape of the predicted probability distribution can become similar to the uniform distribution when the model cannot infer properly. We exploit this observation for detecting out-of-scope (OOS) utterances in conversational systems. Specifically, we propose a zero-shot post-processing step, called Distance-to-Uniform (D2U), exploiting not only the classification confidence score, but the shape of the entire output distribution. We later combine it with a learning procedure that uses D2U for loss calculation in the supervised setup. We conduct experiments using six publicly available datasets. Experimental results show that the performance of OOS detection is improved with our post-processing when there is no OOS training data, as well as with D2U learning procedure when OOS training data is available.

NAACL 2022

D2U: Distance-to-Uniform Learning for Out-of-Scope Detection

out-of-scope detection

voice assistants

dialogue systems

## 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

Although many pretrained models exist for text or images, there have been relatively fewer attempts to train representations specifically for dialog understanding. Prior works usually relied on finetuned representations based on generic text representation models like BERT or GPT-2. But such language modeling pretraining objectives do not take the structural information of conversational text into consideration. Although generative dialog models can learn structural features too, we argue that the structure-unaware word-by-word generation is not suitable for effective conversation modeling. We empirically demonstrate that such representations do not perform consistently across various dialog understanding tasks. Hence, we propose a structure-aware Mutual Information based loss-function DMI (Discourse Mutual Information) for training dialog-representation models, that additionally captures the inherent uncertainty in response prediction. Extensive evaluation on nine diverse dialog modeling tasks shows that our proposed DMI-based models outperform strong baselines by significant margins.

Representation Learning for Conversational Data using Discourse Mutual Information Maximization

In empathetic conversations, humans express their empathy to others with empathetic intents. However, most existing empathetic conversational methods suffer from a lack of empathetic intents, which leads to monotonous empathy. To address the bias of the empathetic intents distribution between empathetic dialogue models and humans, we propose a novel model to generate empathetic responses with human-consistent empathetic intents, EmpHi for short. Precisely, EmpHi learns the distribution of potential empathetic intents with a discrete latent variable, then combines both implicit and explicit intent representation to generate responses with various empathetic intents. Experiments show that EmpHi outperforms state-of-the-art models in terms of empathy, relevance, and diversity on both automatic and human evaluation. Moreover, the case studies demonstrate the high interpretability and outstanding performance of our model.

EmpHi: Generating Empathetic Responses with Human-like Intents

A repetition is a response that repeats words in the previous speaker's utterance in a dialogue. Repetitions are essential in communication to build trust with others, as investigated in linguistic studies. In this work, we focus on repetition generation. To the best of our knowledge, this is the first neural approach to address repetition generation. We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding. We conducted automatic and human evaluations involving applying these methods to the pre-trained language model T5 for generating repetitions. The experimental results indicate that our methods outperformed baselines in both evaluations.

Generating Repetitions with Appropriate Repeated Words

Recent studies on the lottery ticket hypothesis (LTH) show that pre-trained language models (PLMs) like BERT contain matching subnetworks that have similar transfer learning performance as the original PLM. These subnetworks are found using magnitude-based pruning. In this paper, we find that the BERT subnetworks have even more potential than these studies have shown. Firstly, we discover that the success of magnitude pruning can be attributed to the preserved pre-training performance, which correlates with the downstream transferability. Inspired by this, we propose to directly optimize the subnetwork structure towards the pre-training objectives, which can better preserve the pre-training performance. Specifically, we train binary masks over model weights on the pre-training tasks, with the aim of preserving the universal transferability of the subnetwork, which is agnostic to any specific downstream tasks. We then fine-tune the subnetworks on the GLUE benchmark and the SQuAD dataset. The results show that, compared with magnitude pruning, mask training can effectively find BERT subnetworks with improved overall performance on downstream tasks. Moreover, our method is also more efficient in searching subnetworks and more advantageous when fine-tuning within a certain range of data scarcity.

Learning to Win Lottery Tickets in BERT Transfer via Task-agnostic Mask Training

In document-level event extraction (DEE) task, event arguments always scatter across sentences (across-sentence issue) and multiple
events may lie in one document (multi-event issue). In this paper, we argue that the relation information of event arguments is of great
significance for addressing the above two issues, and propose a new DEE framework which can model the relation dependencies, called
Relation-augmented Document-level Event Extraction (ReDEE). More specifically, this framework features a novel and tailored transformer,
named as Relation-augmented Attention Transformer (RAAT). RAAT is scalable to capture multi-scale and multi-amount argument relations. To further leverage relation information, we introduce a separate event relation prediction task and adopt multi-task learning method to explicitly enhance event extraction performance. Extensive experiments demonstrate the effectiveness of the proposed method, which can achieve state-of-the-art performance on two public datasets.Our code is available at https://github.com/TencentYoutuResearch/RAAT.

RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction

Entities lie in the heart of biomedical natural language understanding, and the biomedical entity linking (EL) task remains challenging due to the fine-grained and diversiform concept names.
Generative methods achieve remarkable performances in general domain EL with less memory usage while requiring expensive pre-training.
Previous biomedical EL methods leverage synonyms from knowledge bases (KB) which is not trivial to inject into a generative method.
In this work, we use a generative approach to model biomedical EL and propose to inject synonyms knowledge in it.
We propose KB-guided pre-training by constructing synthetic samples with synonyms and definitions from KB and require the model to recover concept names.
We also propose synonyms-aware fine-tuning to select concept names for training, and propose decoder prompt and multi-synonyms constrained prefix tree for inference.
Our method achieves state-of-the-art results on several biomedical EL tasks without candidate selection which displays the effectiveness of proposed pre-training and fine-tuning strategies. The source code is available at \urlhttps://github.com/Yuanhy1997/GenBioEL.

Generative Biomedical Entity Linking via Knowledge Base-Guided Pre-training and Synonyms-Aware Fine-tuning

The ability to extract entities and their relations from unstructured text is essential for the automated maintenance of large-scale knowledge graphs. To keep a knowledge graph up-to-date, an extractor needs not only the ability to recall the triples it encountered during training, but also the ability to extract the new triples from the context that it has never seen before. In this paper, we show that although existing extraction models are able to easily memorize and recall already seen triples, they cannot generalize effectively for unseen triples. This alarming observation was previously unknown due to the composition of the test sets of the go-to benchmark datasets, which turns out to contain only 2% unseen data, rendering them incapable to measure the generalization performance. To separately measure the generalization performance from the memorization performance, we emphasize unseen data by rearranging datasets, sifting out training instances, or augmenting test sets. In addition to that, we present a simple yet effective augmentation technique to promote generalization of existing extraction models, and experimentally confirm that the proposed method can significantly increase the generalization performance of existing models.

Does it Really Generalize Well on Unseen Data? Systematic Evaluation of Relational Triple Extraction Methods

We propose a global entity disambiguation (ED) model based on BERT. To capture global contextual information for ED, our model treats not only words but also entities as input tokens, and solves the task by sequentially resolving mentions to their referent entities and using resolved entities as inputs at each step. We train the model using a large entity-annotated corpus obtained from Wikipedia. We achieve new state-of-the-art results on five standard ED datasets: AIDA-CoNLL, MSNBC, AQUAINT, ACE2004, and WNED-WIKI.  The source code and model checkpoint are available at https://github.com/studio-ousia/luke.

Global Entity Disambiguation with BERT

In document-level event argument extraction, an argument is likely to appear multiple times in different expressions in the document. The redundancy of arguments underlying multiple sentences is beneficial but is often overlooked. In addition, in event argument extraction, most entities are regarded as class “others", i.e. Universum class, which is defined as a collection of samples that do not belong to any class of interest. Universum class is composed of heterogeneous entities without typical common features. Classifiers trained by cross entropy loss could easily misclassify the Universum class because of their open decision boundary. In this paper, to make use of redundant event information underlying a document, we build an entity coreference graph with the graph2token module to produce a comprehensive and coreference-aware representation for every entity and then build an entity summary graph to merge the multiple extraction results. To better classify Universum class, we propose a new loss function to build classifiers with closed boundaries. Experimental results show that our model outperforms the previous state-of-the-art models by 3.35% in F1-score.

Document-Level Event Argument Extraction by Leveraging Redundant Information and Closed Boundary Loss

The task of modal dependency parsing aims to parse a text into its modal dependency structure, which is a representation for the factuality of events in the text. We design a modal dependency parser that is based on priming pre-trained language models, and evaluate the parser on two data sets. Compared to baselines, we show an improvement of 2.6% in F-score for English and 4.6% for Chinese. To the best of our knowledge, this is also the first work on Chinese modal dependency parsing.

Downloads

Next from NAACL 2022

Representation Learning for Conversational Data using Discourse Mutual Information Maximization

Similar lecture

On Transferability of Prompt Tuning for Natural Language Processing