United States

We observe that current dialogue summarization models have flaws that may not be well exposed by frequently used metrics such as ROUGE. In our paper, we re-evaluate 18 categories of metrics in terms of four dimensions: coherence, consistency, fluency, and relevance, with a unified human evaluation of various models in dialogue summarization for the first time. Some noteworthy trends which are different from the conventional summarization tasks are identified.

NAACL 2022

DialSummEval: Revisiting Summarization Evaluation for Dialogues

automatic evaluation metrics

dialogue summarization

evaluation

stages 

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

First established in 1965, the biennial COLING conference is held in diverse parts of the globe and attracts participants from both top-ranked research centers and emerging countries. Today, the most important developments in our field are taking place not only in universities and academic research institutes, but also in industrial research departments and in technological startups. COLING conferences provide opportunities for all these communities to showcase their exciting developments.

COLING 2020

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for natural language processing and computational linguistics. Often grouped within the field of artificial intelligence, but actually pre-dating the development of artificial intelligence, advances in computational linguistics and natural language processing are now some of the major drivers behind the use of artificial intelligence for commercial and social applications – for example, on-line search, machine translation and with voice-assisted conversational devices.

technical paper

## 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

Large pre-trained neural language models have supported the effectiveness of many NLP tasks, yet are still prone to generating toxic language hindering the safety of their use. Using empathetic data, we improve over recent work on controllable text generation that aims to reduce the toxicity of generated text. We find we are able to dramatically reduce the size of fine-tuning data to 7.5-30k samples while at the same time making significant improvements over state-of-the-art toxicity mitigation of up to 3.4% absolute reduction (26% relative) from the original work on 2.3m samples, by strategically sampling data based on empathy scores. We observe that the degree of improvement is subject to specific communication components of empathy. In particular, the cognitive components of empathy significantly beat the original dataset in almost all experiments, while emotional empathy was tied to less improvement and even underperforming random samples of the original data. This is a particularly implicative insight for NLP work concerning empathy as until recently the research and resources built for it have exclusively considered empathy as an emotional concept.

Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy

Providing conversation models with background knowledge has been shown to make open-domain dialogues more informative and engaging. Existing models treat knowledge selection as a sentence ranking or classification problem where each sentence is handled individually, ignoring the internal semantic connection between sentences. In this work, we propose to automatically convert the background knowledge documents into document semantic graphs and then perform knowledge selection over such graphs. Our document semantic graphs preserve sentence-level information through the use of sentence nodes and provide concept connections between sentences. We apply multi-task learning to perform sentence-level knowledge selection and concept-level knowledge selection, showing that it improves sentence-level selection. Our experiments show that our semantic graph-based knowledge selection improves over sentence selection baselines for both the knowledge selection task and the end-to-end response generation task on HollE and improves generalization on unseen topics in WoW.

Enhancing Knowledge Selection for Grounded Dialogues via Document Semantic Graphs

It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations. Recent studies have shown that fine-tuning pre-trained language models with a small amount of labeled utterances from public benchmarks in a supervised manner is extremely helpful. However, we find that supervised pre-training yields an anisotropic feature space, which may suppress the expressive power of the semantic representations. Inspired by recent research in isotropization, we propose to improve supervised pre-training by regularizing the feature space towards isotropy. We propose two regularizers based on contrastive learning and correlation matrix respectively, and demonstrate their effectiveness through extensive experiments. Our main finding is that it is promising to regularize supervised pre-training with isotropization to further improve the performance of few-shot intent detection.

Fine-tuning Pre-trained Language Models for Few-shot Intent Detection: Supervised Pre-training and Isotropization

In recent years, transformer-based coreference resolution systems have achieved remarkable improvements on the CoNLL dataset. However, how coreference resolvers can benefit from discourse coherence is still an open question. In this paper, we propose to incorporate centering transitions derived from centering theory in the form of a graph into a neural coreference model. Our method improves the performance over the SOTA baselines, especially on pronoun resolution in long documents, formal well-structured text, and clusters with scattered mentions.

Incorporating Centering Theory into Neural Coreference Resolution

As using they/them as personal pronouns becomes increasingly common in English, it is important that coreference resolution systems work as well for individuals who use personal "they” as they do for those who use gendered personal pronouns. We introduce a new benchmark for coreference resolution systems which evaluates singular personal “they” recognition. Using these WinoNB schemas, we evaluate a number of publicly available coreference resolution systems and confirm their bias toward resolving “they” pronouns as plural.

Recognition of They/Them as Singular Personal Pronouns in Coreference Resolution

Unsupervised relation extraction aims to ex- tract the relationship between entities from natural language sentences without prior in- formation on relational scope or distribution. Existing works either utilize self-supervised schemes to refine relational feature signals by iteratively leveraging adaptive clustering and classification that provoke gradual drift prob- lems, or adopt instance-wise contrastive learn- ing which unreasonably pushes apart those sentence pairs that are semantically similar. To overcome these defects, we propose a novel contrastive learning framework named HiURE, which has the capability to derive hierarchical signals from relational feature space using cross hierarchy attention and effec- tively optimize relation representation of sen- tences under exemplar-wise contrastive learn- ing. Experimental results on two public datasets demonstrate the advanced effective- ness and robustness of HiURE on unsuper- vised relation extraction when compared with state-of-the-art models.

HiURE: Hierarchical Exemplar Contrastive Learning for Unsupervised Relation Extraction

There has been a growing interest in interpreting the underlying dynamics of Transformers. While self-attention patterns were initially deemed as the primary option, recent studies have shown that integrating other components can yield more accurate explanations. This paper introduces a novel token attribution analysis method that incorporates all the components in the encoder block and aggregates this throughout layers. Through extensive quantitative and qualitative experiments, we demonstrate that our method can produce faithful and meaningful global token attributions. Our experiments reveal that incorporating almost every encoder component results in increasingly more accurate analysis in both local (single layer) and global (the whole model) settings. Our global attribution analysis significantly outperforms previous methods on various tasks regarding correlation with gradient-based saliency scores. Our code is freely available at https://github.com/mohsenfayyaz/GlobEnc .

GlobEnc: Quantifying Global Token Attribution by Incorporating the Whole Encoder Layer in Transformers

Large pretrained language models (LMs) have become the central building block of many NLP applications. Training these models requires ever more computational resources and most of the existing models are trained on English text only. It is exceedingly expensive to train these models in other languages. To alleviate this problem, we introduce a novel method -- called WECHSEL -- to efficiently and effectively transfer pretrained LMs to new languages. WECHSEL can be applied to any model which uses subword-based tokenization and learns an embedding for each subword. The tokenizer of the source model (in English) is replaced with a tokenizer in the target language and token embeddings are initialized such that they are semantically similar to the English tokens by utilizing multilingual static word embeddings covering English and the target language. We use WECHSEL to transfer the English RoBERTa and GPT-2 models to four languages (French, German, Chinese and Swahili). We also study the benefits of our method on very low-resource languages. WECHSEL improves over proposed methods for cross-lingual parameter transfer and outperforms models of comparable size trained from scratch with up to 64x less training effort. Our method makes training large language models for new languages more accessible and less damaging to the environment. We make our code and models publicly available.

WECHSEL: Effective initialization of subword embeddings for cross-lingual transfer of monolingual language models

Non-autoregressive neural machine translation (NAT) suffers from the multi-modality problem: the source sentence may have multiple correct translations, but the loss function is calculated only according to the reference sentence. Sequence-level knowledge distillation makes the target more deterministic by replacing the target with the output from an autoregressive model. However, the multi-modality problem in the distilled dataset is still nonnegligible. Furthermore, learning from a specific teacher limits the upper bound of the model capability, restricting the potential of NAT models. In this paper, we argue that one reference is not enough and propose diverse distillation with reference selection (DDRS) for NAT. Specifically, we first propose a method called SeedDiv for diverse machine translation, which enables us to generate a dataset containing multiple high-quality reference translations for each source sentence. During the training, we compare the NAT output with all references and select the one that best fits the NAT output to train the model. Experiments on widely-used machine translation benchmarks demonstrate the effectiveness of DDRS, which achieves 29.82 BLEU with only one decoding pass on WMT14 En-De, improving the state-of-the-art performance for NAT by over 1 BLEU.\footnote{Source code: https://github.com/ictnlp/DDRS-NAT.}

One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translation

The application of supervised methods to automatic summarization requires the availability of adequate corpora consisting of a set of document-summary pairs. As in most Natural Language Processing tasks, the great majority of available datasets for summarization are in English, making it difficult to develop automatic summarization models for other languages. Although Spanish is gradually forming part of some recent summarization corpora, it is not the same for minority languages such as Catalan.
In this work, we describe the construction of a corpus of Catalan and Spanish newspapers, the Dataset for Automatic summarization of Catalan and Spanish newspaper Articles (DACSA) corpus. It is a high-quality large-scale corpus that can be used to train summarization models for Catalan and Spanish.
We have carried out an analysis of the corpus, both in terms of the style of the summaries and the difficulty of the summarization task. In particular, we have used a set of well-known metrics in the summarization field in order to characterize the corpus. Additionally, for benchmarking purposes, we have evaluated the performances of some extractive and abstractive summarization systems on the DACSA corpus.

DialSummEval: Revisiting Summarization Evaluation for Dialogues

Downloads

Next from NAACL 2022

Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy

Similar lecture

Would you describe a leopard as yellow? Evaluating crowd annotations with justified and informative disagreement

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

DialSummEval: Revisiting Summarization Evaluation for Dialogues

.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 2022

Mitigating Toxic Degeneration with Empathetic Data: Exploring the Relationship Between Toxicity and Empathy

Similar lecture

Would you describe a leopard as yellow? Evaluating crowd annotations with justified and informative disagreement

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads