Korea, Republic of

Traditional training paradigms for extractive and abstractive summarization systems always only use token-level or sentence-level training objectives. However, the output summary is always evaluated from summary-level which leads to the inconsistency in training and evalu- ation. In this paper, we propose a Contrastive Learning based re-ranking framework for one- stage summarization called COLO. By mod- eling a contrastive objective, we show that the summarization model is able to directly gener- ate summaries according to the summary-level score without additional modules and parame- ters. Extensive experiments demonstrate that COLO boosts the extractive and abstractive re- sults of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score while preserving the parameter efficiency and inference efficiency. Compared with state-of- the-art multi-stage systems, we save more than 100 GPU training hours and obtaining 3~8 speed-up ratio during inference while main- taining comparable results.

COLING 2022

CoLo: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization

text summarization

re-ranking

contrastive learning

[![](https://assets.underline.io/uploads/markdown_image/1/image/81a3c0317d24f663b49b996875024d45.png)](https://aclanthology.org/volumes/2022.coling-1/)



### THE CONFERENCE WE KNOW AND WE WANT.
**COLING**, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

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 including tech-startups. COLING provides opportunities for all these communities to showcase their exciting discovery.

In fall of 2022, COLING will be held in Gyeongju in a hybrid format. All participants can either present at the venue site or join virtually. As more people get vaccinated, we are happy to provide safer environments for our colleagues. We believe that COLING 2022 will be one of the conferences, free from the pandemic. The hybrid format gives presenters and sponsors a valuable opportunity to promote their companies in both an online and in-person venue. For the first time in a long time, customers can interact with their sponsor's products first-hand. The online venue, too, gives sponsors the chance to network with those unable to attend the in-person session.

The hybrid format ultimately lends itself to greater exposure for our sponsors: COLING2022 will let you reach more potential partners and customers than ever before!<br><br><br>

To gain access to this event page you are required to register.<br> Find more information and pay the registration fee on event the organizer’s website **[https://coling2022.org/reg](https://coling2022.org/reg)**

COLING, the International Conference on Computational Linguistics, is one of the premier conferences for the natural language processing and computational linguistics.

poster

This presentation will introduce our paper "Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling". The paper's abstract is as follows:
Neural text generation models are likely to suffer from the low-diversity problem. Various decoding strategies and training-based methods have been proposed to promote diversity only by exploiting contextual features, but rarely do they consider incorporating syntactic structure clues. In this work, we propose using linguistic annotation, i.e., part-of-speech (POS), to guide the text generation. In detail, we introduce POS Guided Softmax to explicitly model two posterior probabilities: (i) next-POS, and (ii) next-token from the vocabulary of the target POS. A POS Guided Sampling strategy is further proposed to address the low-diversity problem by enriching the diversity of POS. Extensive experiments and human evaluations show that, compared with existing state-of-the-art methods, our POS Guided Softmax and Sampling (POSG) can generate more diverse text while maintaining comparable quality.

Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling

Aspect Sentiment Triplet Extraction (ASTE) aims at extracting triplets from a given sentence, where each triplet includes an aspect, its sentiment polarity, and a corresponding opinion explaining the polarity. Existing methods are poor at detecting complicated relations between aspects and opinions as well as classifying multiple sentiment polarities in a sentence. Detecting unclear boundaries of multi-word aspects and opinions is also a challenge. In this paper, we propose a Multi-Task Dual-Tree Network (MTDTN) to address these issues. We employ a constituency tree and a modified dependency tree in two sub-tasks of Aspect Opinion Co-Extraction (AOCE) and ASTE, respectively. To enhance the information interaction between the two sub-tasks, we further design a Transition-Based Inference Strategy (TBIS) that transfers the boundary information from tags of AOCE to ASTE through a transition matrix. Extensive experiments are conducted on four popular datasets, and the results show the effectiveness of our model.

A Multi-Task Dual-Tree Network for Aspect Sentiment Triplet Extraction

Treebank selection for parsing evaluation and the spurious effects that might arise from a biased choice have not been explored in detail. This paper studies how evaluating on a single subset of treebanks can lead to weak conclusions. First, we take a few contrasting parsers, and run them on subsets of treebanks proposed in previous work, whose use was justified (or not) on criteria such as typology or data scarcity. Second, we run a large-scale version of this experiment, create vast amounts of random subsets of treebanks, and compare on them many parsers whose scores are available. The results show substantial variability across subsets and that although establishing guidelines for good treebank selection is hard, it is possible to detect potentially harmful strategies.

The Fragility of Multi-Treebank Parsing Evaluation

Recently, many task-oriented dialogue systems
need to serve users in different languages. However,
it is time-consuming to collect enough
data of each language for training. Thus, zeroshot
adaptation of cross-lingual task-oriented
dialog systems has been studied. Most of existing
methods consider the word-level alignments
to conduct two main tasks for taskoriented
dialogue system, i.e., intent detection
and slot filling, and they rarely explore the dependency
relations among these two tasks. In
this paper, we propose a hierarchical framework
to classify the pre-defined intents in the
high-level and fulfill slot filling under the guidance
of intent in the low-level. Particularly, we
incorporate sentence-level alignment among
different languages to enhance the performance
of intent detection. The extensive experiments
report that our proposed method achieves the
SOTA performance on the public task-oriented
dialog dataset.

HCLD: A Hierarchical Framework for Zero-shot Cross-lingual Dialogue System

Cross-lingual Abstract Meaning Representation (AMR) parsers are currently evaluated in comparison to gold English AMRs, despite parsing a language other than English, due to the lack of multilingual AMR evaluation metrics. This evaluation practice is problematic because of the established effect of source language on AMR structure. In this work, we present three multilingual adaptations of monolingual AMR evaluation metrics and compare the performance of these metrics to sentence-level human judgments. We then use our most highly correlated metric to evaluate the output of state-of-the-art cross-lingual AMR parsers, finding that Smatch may still be a useful metric in comparison to gold English AMRs, while our multilingual adaptation of S2match (XS2match) is best for comparison with gold in-language AMRs.

Accounting for Language Effect in the Evaluation of Cross-lingual AMR Parsers

Word ordering is a constrained language generation task taking unordered words as input. Existing work uses linear models and neural networks for the task, yet pre-trained language models have not been studied in word ordering, let alone why they help. We use BART as an instance and show its effectiveness in the task. To explain why BART helps word ordering, we extend analysis with probing and empirically identify that syntactic dependency knowledge in BART is a reliable explanation. We also report performance gains with BART in the related partial tree linearization task, which readily extends our analysis.

On the Role of Pre-trained Language Models in Word Ordering: A Case Study with BART

Predicting word embeddings for out of vocabulary words remains an important challenge for NLP tools. Word embedding models only include terms that occur a sufficient number of times in their training corpora. Word embedding vector models attempt to approximate information about a word not in their vocabularies. We propose a fast method for predicting vectors for out of vocabulary terms that makes use of the surrounding terms of the unknown term and the hidden context layer of the word2vec model. We propose this method as a strong baseline in the sense that 1) while it does not surpass all state-of-the-art methods, it surpasses several techniques for vector prediction on benchmark tasks, 2) even when it underperforms, the margin is small retaining competitive performance in downstream tasks, and 3) it is inexpensive to compute, requiring no additional training stage. We also show that our technique can be incorporated into existing methods to achieve a new state-of-the-art on the word vector prediction problem.

COIN – An Inexpensive and Strong Baseline for Predicting Out of Vocabulary Word Embeddings

As we know, people are able to use thousands of languages to describe images, but languages only share one visual world. Multi-modal Machine Translation aims to optimize the conventional text-only machine translation systems by using multi-modal information, which has received growing research attentions in the fields of CV and NLP, recently.

Noise-robust Cross-modal Interactive Learning with Text2image Mask for Multi-modal Neural Machine Translation

Sentiment analysis in social media is challenging since posts are short of context. As
a popular way to express emotion on social media, stickers related to these posts can supplement missing sentiments and help identify sentiments precisely. However, research about stickers has not been investigated further. To this end, we present a Chinese sticker-based multimodal dataset for the sentiment analysis
task (CSMSA). Compared with previous realworld photo-based multimodal datasets, the CSMSA dataset focuses on stickers, conveying more vivid and moving emotions. The sticker-based multimodal sentiment analysis task is challenging in three aspects: inherent multimodality of stickers, significant interseries variations between stickers, and complex multimodal sentiment fusion. We propose SAMSAM to address the above three challenges. Our model introduces a flexible masked self-attention mechanism to allow the dynamic interaction between post texts and stickers. The experimental results indicate that our model performs best compared with other models. More researches need to be devoted to this field.

Towards Exploiting Sticker for Multimodal Sentiment Analysis in Social Media: A New Dataset and Baseline

Zero-shot learning for Dialogue State Tracking (DST) focuses on generalizing to an unseen domain without the expense of collecting indomain data. However, previous zero-shot DST methods ignore the slot dependencies in a multidomain dialogue, resulting in sub-optimal performances when adapting to unseen domains.
In this paper, we utilize slot prompts combination, slot values demonstration, and slot constraint object to model the slot-slot dependency, slot-value dependency and slot-context dependency respectively. Specifically, each slot prompt consists of a slot-specific prompt and a slot-shared prompt to capture the shared knowledge across different domains. Experimental results show the effectiveness of our proposed method over existing state-of-art generation methods under zero-shot/few-shot settings.

Downloads

Next from COLING 2022

Diversifying Neural Text Generation with Part-of-Speech Guided Softmax and Sampling

Similar lecture

Improving Abstractive Dialogue Summarization with Speaker-Aware Supervised Contrastive Learning