Taiwan

One of the challenges of developing a summarization model arises from the difficulty in measuring the factual inconsistency of the generated text. In this study, we reinterpret the decoder overconfidence-regularizing objective suggested in (Miao et al., 2021) as a hallucination risk measurement to better estimate the quality of generated summaries. We propose a reference-free metric, HaRiM+, which only requires an off-the-shelf summarization model to compute the hallucination risk based on token likelihoods. Deploying it requires no additional training of models or ad-hoc modules, which usually need alignment to human judgments. For summary-quality estimation, HaRiM+ records state-of-the-art correlation to human judgment on three summary-quality annotation sets: FRANK, QAGS, and SummEval. We hope that our work, which merits the use of summarization models, facilitates the progress of both automated evaluation and generation of summary.

IJCNLP-AACL 2022

Evaluating Summary Quality with Hallucination Risk

hallucination

summarization

evaluation

## 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/)

NAACL 2022

2022 Annual Conference of the North American Chapter of the Association for Computational Linguistics

technical paper

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP).

A registration is required to access this event. Access to the event site will be granted to all registered attendees on **November 16th**. If you have not already done so, please register using the link below:
 
 https://conference.iis.sinica.edu.tw/servlet/Register?ConferenceID=411

Registration Is Required

The AACL, Asia-Pacific Chapter of the Association for Computational Linguistics, and the AFNLP, Asian Federation of Natural Language Processing, invite you to participate in the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (AACL) and the 10th International Joint Conference on Natural Language Processing (IJCNLP). 

We present a novel architecture for explainable modeling of task-oriented dialogues with discrete latent variables to represent dialogue actions. Our model is based on variational recurrent neural networks (VRNN) and requires no explicit annotation of semantic information. Unlike previous works, our approach models the system and user turns separately and performs database query modeling, which makes the model applicable to task-oriented dialogues while producing easily interpretable action latent variables. We show that our model outperforms previous approaches with less supervision in terms of perplexity and BLEU on three datasets, and we propose a way to measure dialogue success without the need for expert annotation. Finally, we propose a novel way to explain semantics of the latent variables with respect to system actions.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.24/)

Learning Interpretable Latent Dialogue Actions With Less Supervision

Complex conversation settings such as persuasion involve communicating changes in attitude or behavior, so users' perspectives need to be addressed, even when not directly related to the topic. In this work, we contribute a novel modular dialogue system framework that seamlessly integrates factual information and social content into persuasive dialogue. Our framework is generalizable to any dialogue tasks that have mixed social and task contents. We conducted a study that compared user evaluations of our framework versus a baseline end-to-end generation model. We found our framework was evaluated more favorably in all dimensions including competence and friendliness, compared to the end-to-end model which does not explicitly handle social content or factual questions

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.31/)

Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue

Communicating efficiently in natural language requires that we often leave information implicit, especially in spontaneous speech. This frequently results in phenomena of incompleteness, such as omitted references, that pose challenges for language processing. In this poster session, we discuss the state of the art in research regarding the automatic processing of such implicit references in dialog scenarios, discuss weaknesses with respect to inconsistencies in task definitions and terminologies, and outline ideas for future work. Among others, these include unification of existing tasks and evaluation metrics, addressing data scarcity, and taking into account model and annotator uncertainties, but we are also excited to exchange new ideas about where this field should head.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.45/)

Towards Implicit References in Dialog

Speakers repeat constructions frequently in dialogue. Due to their peculiar information-theoretic properties, repetitions can be thought of as a strategy for cost-effective communication. In this study, we focus on the repetition of lexicalised constructions -- i.e., recurring multi-word units -- in English open-domain spoken dialogues. We hypothesise that speakers use construction repetition to mitigate information rate, leading to an overall decrease in utterance information content over the course of a dialogue. We conduct a quantitative analysis, measuring the information content of constructions and that of their containing utterances, estimating information content with an adaptive neural language model. We observe that construction usage lowers the information content of utterances. This facilitating effect (i) increases throughout dialogues, (ii) is boosted by repetition, (iii) grows as a function of repetition frequency and density, and (iv) is stronger for repetitions of referential constructions.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.51/)

Construction Repetition Reduces Information Rate in Dialogue

Recent language generative models are mostly trained on large-scale datasets, while in some real scenarios, the training datasets are often expensive to obtain and would be small-scale. In this paper we investigate the challenging task of less-data constrained generation, especially when the generated news headlines are short yet expected by readers to keep readable and informative simultaneously. We highlight the key information modeling task and propose a novel duality fine-tuning method by formally defining the probabilistic duality constraints between key information prediction and headline generation tasks. The proposed method can capture more information from limited data, build connections between separate tasks, and is suitable for less-data constrained generation tasks. Furthermore, the method can leverage various pre-trained generative regimes, e.g., autoregressive and encoder-decoder models. We conduct extensive experiments to demonstrate that our method is effective and efficient to achieve improved performance in terms of language modeling metric and informativeness correctness metric on two public datasets.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-main.5/)

Leveraging Key Information Modeling to Improve Less-Data Constrained News Headline Generation via Duality Fine-Tuning

Automatic Readability Assessment aims at assigning a complexity level to a given text, which could help improve the accessibility to information in specific domains, such as the administrative one. In this paper, we investigate the behavior of a Neural Pairwise Ranking Model (NPRM) for sentence-level readability assessment of Italian administrative texts.
To deal with data scarcity, we experiment with cross-lingual, cross- and in-domain approaches, and test our models on Admin-It, a new parallel corpus in the Italian administrative language, containing sentences simplified using three different rewriting strategies.
We show that NPRMs are effective in zero-shot scenarios (∼0.78 ranking accuracy), especially with ranking pairs containing simplifications produced by overall rewriting at the sentence-level, and that the best results are obtained by adding in-domain data (achieving perfect performance for such sentence pairs). Finally, we investigate where NPRMs failed, showing that the characteristics of the data used for fine-tuning, rather than its size, have a bigger effect on a model's performance.

Neural Readability Pairwise Ranking for Sentences in Italian Administrative Language

Argumentative dialogue is an important process where speakers discuss a specific theme for consensus building or decision making. In previous studies for generating consistent argumentative dialogue, retrieval-based methods with hand-crafted argumentation structures have been used. In this study, we propose a method to generate natural argumentative dialogues by combining an argumentation structure and language model. We trained the language model to rewrite a proposition of an argumentation structure on the basis of its information, such as keywords and stance, into the next utterance while considering its context, and we used the model to rewrite propositions in the argumentation structure. We manually evaluated the generated dialogues and found that the proposed method significantly improved the naturalness of dialogues without losing consistency of argumentation.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.9/)

Combining Argumentation Structure and Language Model for Generating Natural Argumentative Dialogue

The presentation gives an introduction of our work on the few-shot dialogue state tracking task, including the task background, the model description and the experimental results.

To view the proceedings, please [click here](https://aclanthology.org/2022.aacl-short.37/)

CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking

Today’s neural NLP can do amazing things, leading some people to expect human-level performance soon. But it also fails spectacularly, in ways we find hard to predict and explain. Is perfection just a matter of doing additional neural architecture engineering and more-advanced training to overcome these problems, or are there deeper reasons for the failures? I argue that trying to understand the nature and reason for failures by couching the necessary operations in terms of symbolic reasoning is a good way to discover what neural networks will remain unable to do despite additional architecture engineering and training.

On the complementarity of neural and symbolic approaches, and on how to transfer between them

I will present research by my lab at the University of Pennsylvania that has focused on a language-centric approach to classic goals in Artificial Intelligence.  The types of research questions that we are addressing are the following: Can we design language models that are better able to reason about other agent's goals by observing steps?  How can AI systems learn commonsense knowledge knowledge about procedures from instructions found on the web?  Should we as AI practitioners design structured schematic representations akin to Shank and Adelson's scripts, or is it more effective to use free-form natural language representations?  Has GPT-3 solved all of our problems?  If so, what's the best drink recipe for a Mai Tai?

Evaluating Summary Quality with Hallucination Risk

Downloads

Next from IJCNLP-AACL 2022

Learning Interpretable Latent Dialogue Actions With Less Supervision

Similar lecture

Does Summary Evaluation Survive Translation to Other Languages?

Evaluating Summary Quality with Hallucination Risk

.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 IJCNLP-AACL 2022

Learning Interpretable Latent Dialogue Actions With Less Supervision

Similar lecture

Does Summary Evaluation Survive Translation to Other Languages?

Downloads