Thailand

Large pretrained models have achieved great success in many natural language processing tasks. However, when they are applied in specific domains, these models suffer from domain shift and bring
challenges in fine-tuning and online serving for latency and capacity constraints. In this paper, we present a general approach to developing small, fast and effective pretrained models for specific domains. This is achieved by adapting the off-the-shelf general pretrained models and performing task-agnostic knowledge distillation in target domains. Specifically, we propose domain-specific vocabulary expansion in the adaptation stage and employ corpus level occurrence probability to choose the size of incremental vocabulary automatically. Then we systematically explore different strategies to compress the large pretrained models for specific domains. We conduct our experiments in the biomedical and computer science domain. The experimental results demonstrate that our approach achieves better performance over the BERT&lt;sub&gt;BASE&lt;/sub&gt;model in domain-specific tasks while 3.3× smaller and 5.1× faster than BERT&lt;sub&gt;BASE&lt;/sub&gt;.
The code and pretrained models are available at &lt;https://aka.ms/adalm&gt;.

IJCNLP-AACL 2021

Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains

incremental vocabulary

continual pretrain

domain adaptation

**Welcome to ACL-IJCNLP 2021!**

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP). 

As in previous years, the program of the conference includes a poster session, tutorials, workshops and demonstrations in addition to the main conference.


We were able to keep the registration fees similar to those charged for the virtual ACL 2020. The one fee allows attendance at the main conference and any/all tutorials and workshops. These fees would be $125 Regular Early and $175 Regular Late; $50 Student Early and $75 Student Late. Early registration closes at midnight July 11, 2021 (Eastern Daylight Time).

**Reminder:** It is ACL’s policy that at least one author of each accepted paper (including ACL Finding papers) must register for the conference.

**Reminder2:** Underline site will open closer to the event. If you already registered you will receive access detail

Registration is now open

The great event is jointly organized by the Association for Computational Linguistics (ACL) and Asian Federation of Natural Language Processing (AFNLP).

Large pretrained models have achieved great success in many natural language processing tasks. However, when they are applied in specific domains, these models suffer from domain shift and bring
challenges in fine-tuning and online serving for latency and capacity constraints. In this paper, we present a general approach to developing small, fast and effective pretrained models for specific domains. This is achieved by adapting the off-the-shelf general pretrained models and performing task-agnostic knowledge distillation in target domains. Specifically, we propose domain-specific vocabulary expansion in the adaptation stage and employ corpus level occurrence probability to choose the size of incremental vocabulary automatically. Then we systematically explore different strategies to compress the large pretrained models for specific domains. We conduct our experiments in the biomedical and computer science domain. The experimental results demonstrate that our approach achieves better performance over the BERT<sub>BASE</sub>model in domain-specific tasks while 3.3× smaller and 5.1× faster than BERT<sub>BASE</sub>.
The code and pretrained models are available at <https://aka.ms/adalm>.

technical paper

Product reviews contain a large number of implicit aspects and implicit opinions. However, most of the existing studies in aspect-based sentiment analysis ignored this problem. In this work, we introduce a new task, named Aspect-Category-Opinion-Sentiment (ACOS) Quadruple Extraction, with the goal to extract all aspect-category-opinion-sentiment quadruples in a review sentence and provide full support for aspect-based sentiment analysis with implicit aspects and opinions. We furthermore construct two new datasets, Restaurant-ACOS and Laptop-ACOS, for this new task, both of which contain the annotations of not only aspect-category-opinion-sentiment quadruples but also implicit aspects and opinions. The former is an extension of the SemEval Restaurant dataset; the latter is a newly collected and annotated Laptop dataset, twice the size of the SemEval Laptop dataset. We finally benchmark the task with four baseline systems. Experiments demonstrate the feasibility of the new task and its effectiveness in extracting and describing implicit aspects and implicit opinions. The two datasets and source code of four systems are publicly released at \url{https://github.com/NUSTM/ACOS}.

Aspect-Category-Opinion-Sentiment Quadruple Extraction with Implicit Aspects and Opinions

Humor recognition has been widely studied as a text classification problem using data-driven approaches. However, most existing work does not examine the actual joke mechanism to understand humor. We break down any joke into two distinct components: the set-up and the punchline, and further explore the special relationship between them. Inspired by the incongruity theory of humor, we model the set-up as the part developing semantic uncertainty, and the punchline disrupting audience expectations. With increasingly powerful language models, we were able to feed the set-up along with the punchline into the GPT-2 language model, and calculate the uncertainty and surprisal values of the jokes. By conducting experiments on the SemEval 2021 Task 7 dataset, we found that these two features have better capabilities of telling jokes from non-jokes, compared with existing baselines.

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Disentanglement of latent representations into content and style spaces has been a commonly employed method for unsupervised text style transfer. These techniques aim to learn the disentangled representations and tweak them to modify the style of a sentence. In this paper, we propose a counterfactual-based method to modify the latent representation, by posing a ‘what-if’ scenario. This simple and disciplined approach also enables a fine-grained control on the transfer strength. We conduct experiments with the proposed methodology on multiple attribute transfer tasks like Sentiment, Formality and Excitement to support our hypothesis.

Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer

he product reviews summarization task aims to automatically produce a short summary for a set of reviews of a given product. Such summaries are expected to aggregate a range of different opinions in a concise, coherent and informative manner. This challenging task gives rise to two shortcomings in existing work. First, summarizers tend to favor generic content that appears in reviews for many different products, resulting in template-like, less informative summaries. Second, as reviewers often disagree on the pros and cons of a given product, summarizers sometimes yield inconsistent, self-contradicting summaries. We propose the PASS system (Perturb-and-Select Summarizer) that employs a large pre-trained Transformer-based model (T5 in our case), which follows a few-shot fine-tuning scheme. A key component of the PASS system relies on applying systematic perturbations to the model’s input during inference, which allows it to generate multiple different summaries per product. We develop a method for ranking these summaries according to desired criteria, coherence in our case, enabling our system to almost entirely avoid the problem of self-contradiction. We compare our system against strong baselines on publicly available datasets, and show that it produces summaries which are more informative, diverse and coherent.

PASS: Perturb-and-Select Summarizer for Product Reviews

In this paper, we address a novel task, Multiple TimeLine Summarization (MTLS), which extends the flexibility and versatility of Time-Line Summarization (TLS). Given any collection of time-stamped news articles, MTLS automatically discovers important yet different stories and generates a corresponding time-line for each story.To achieve this, we propose a novel unsupervised summarization framework based on two-stage affinity propagation. We also introduce a quantitative evaluation measure for MTLS based on previousTLS evaluation methods. Experimental results show that our MTLS framework demonstrates high effectiveness and MTLS task can give bet-ter results than TLS.

Multi-TimeLine Summarization (MTLS): Improving Timeline Summarization by Generating Multiple Summaries

Link prediction on knowledge graphs (KGs) is a key research topic. Previous work mainly focused on binary relations, paying less attention to higher-arity relations although they are ubiquitous in real-world KGs. This paper considers link prediction upon n-ary relational facts and proposes a graph-based approach to this task. The key to our approach is to represent the n-ary structure of a fact as a small heterogeneous graph, and model this graph with edge-biased fully-connected attention. The fully-connected attention captures universal inter-vertex interactions, while with edge-aware attentive biases to particularly encode the graph structure and its heterogeneity. In this fashion, our approach fully models global and local dependencies in each n-ary fact, and hence can more effectively capture associations therein. Extensive evaluation verifies the effectiveness and superiority of our approach. It performs substantially and consistently better than current state-of-the-art across a variety of n-ary relational benchmarks. Our code is publicly available.

Link Prediction on N-ary Relational Facts: A Graph-based Approach

Multi-task benchmarks such as GLUE and SuperGLUE have driven great progress of pretraining and transfer learning in Natural Language Processing (NLP). These benchmarks mostly focus on a range of Natural Language Understanding (NLU) tasks, without considering the Natural Language Generation (NLG) models. In this paper, we present the General Language Generation Evaluation (GLGE), a new multi-task benchmark for evaluating the generalization capabilities of NLG models across eight language generation tasks. For each task, we continue to design three subtasks in terms of task difficulty (GLGE-Easy, GLGE-Medium, and GLGE-Hard). This introduces 24 subtasks to comprehensively compare model performance. To encourage research on pretraining and transfer learning on NLG models, we make GLGE publicly available and build a leaderboard with strong baselines including MASS, BART, and ProphetNet.

GLGE: A New General Language Generation Evaluation Benchmark

Pre-trained language models such as BERT have exhibited remarkable performances in many tasks in natural language understanding (NLU). The tokens in the models are usually fine-grained in the sense that for languages like English they are words or sub-words and for languages like Chinese they are characters. In English, for example, there are multi-word expressions which form natural lexical units and thus the use of coarse-grained tokenization also appears to be reasonable. In fact, both fine-grained and coarse-grained tokenizations have advantages and disadvantages for learning of pre-trained language models. In this paper, we propose a novel pre-trained language model, referred to as AMBERT (A Multi-grained BERT), on the basis of both fine-grained and coarse-grained tokenizations. For English, AMBERT takes both the sequence of words (fine-grained tokens) and the sequence of phrases (coarse-grained tokens) as input after tokenization, employs one encoder for processing the sequence of words and the other encoder for processing the sequence of the phrases, utilizes shared parameters between the two encoders, and finally creates a sequence of contextualized representations of the words and a sequence of contextualized representations of the phrases. Experiments have been conducted on benchmark datasets for Chinese and English, including CLUE, GLUE, SQuAD and RACE. The results show that AMBERT can outperform BERT in all cases, particularly the improvements are significant for Chinese. We also develop a method to improve the efficiency of AMBERT in inference, which still performs better than BERT with the same computational cost as BERT.

AMBERT: A Pre-trained Language Model with Multi-Grained Tokenization

Visual dialogue is a challenging task since it needs to answer a series of coherent questions on the basis of understanding the visual environment. Previous studies focus on the implicit exploration of multimodal co-reference by implicitly attending to spatial image features or object-level image features but neglect the importance of locating the objects explicitly in the visual content, which is associated with entities in the textual content. Therefore, in this paper we propose a {\bf M}ultimodal {\bf I}ncremental {\bf T}ransformer with {\bf V}isual {\bf G}rounding, named MITVG, which consists of two key parts: visual grounding and multimodal incremental transformer. Visual grounding aims to explicitly locate related objects in the image guided by textual entities, which helps the model exclude the visual content that does not need attention. On the basis of visual grounding, the multimodal incremental transformer encodes the multi-turn dialogue history combined with visual scene step by step according to the order of the dialogue and then generates a contextually and visually coherent response. Experimental results on the VisDial v0.9 and v1.0 datasets demonstrate the superiority of the proposed model, which achieves the new state-of-the-art results on substantial metrics.

Multimodal Incremental Transformer with Visual Grounding for Visual Dialogue Generation

Dialogue policy learning, a subtask to determine the content of system response generation and the degree of task completion, is essential for task-oriented dialogue systems. However, the unbalanced distribution of system actions in dialogue datasets often causes a system difficulty in learning to generate desired actions and responses. In this paper, we propose a retrieve-and-memorize framework to enhance the learning of system actions. Specially, we first design a neural context-aware retrieval module to retrieve multiple candidate system actions from the training set given a dialogue context. Then, we propose a memory-augmented multi-decoder network to generate the system actions conditioned on the candidate actions, which allows the network to adaptively select key information in the candidate actions and neglect noise. We conduct experiments on the large-scale multi-domain task-oriented dialogue dataset MultiWOZ 2.0 and MultiWOZ 2.1. Experimental results show that our method achieves favorable improvements over several state-of-the-art models in the context-to-response generation task.

Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains

Downloads

Next from IJCNLP-AACL 2021

Aspect-Category-Opinion-Sentiment Quadruple Extraction with Implicit Aspects and Opinions

Similar lecture

Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Adapt-and-Distill: Developing Small, Fast and Effective Pretrained Language Models for Domains

.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 2021

Aspect-Category-Opinion-Sentiment Quadruple Extraction with Implicit Aspects and Opinions

Similar lecture

Crowdsourcing Learning as Domain Adaptation: A Case Study on Named Entity Recognition

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES

Downloads