Thailand

Transformer is important for text modeling. However, it has difficulty in handling long documents due to the quadratic complexity with input text length. In order to handle this problem, we propose a hierarchical interactive Transformer (Hi-Transformer) for efficient and effective long document modeling. Hi-Transformer models documents in a hierarchical way, i.e., first learns sentence representations and then learns document representations. It can effectively reduce the complexity and meanwhile capture global document context in the modeling of each sentence. More specifically, we first use a sentence Transformer to learn the representations of each sentence. Then we use a document Transformer to model the global document context from these sentence representations. Next, we use another sentence Transformer to enhance sentence modeling using the global document context. Finally, we use hierarchical pooling method to obtain document embedding. Extensive experiments on three benchmark datasets validate the efficiency and effectiveness of Hi-Transformer in long document modeling.

ACL-IJCNLP 2021

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

efficient transformer

hierarchical transformer

long document modeling

transformer

**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).

poster

Personalized news recommendation methods are widely used in online news services. These methods usually recommend news based on the matching between news content and user interest inferred from historical behaviors. However, these methods usually have difficulties in making accurate recommendations to cold-start users, and tend to recommend similar news with those users have read. In general, popular news usually contain important information and can attract users with different interests. Besides, they are usually diverse in content and topic. Thus, in this paper we propose to incorporate news popularity information to alleviate the cold-start and diversity problems for personalized news recommendation. In our method, the ranking score for recommending a candidate news to a target user is the combination of a personalized matching score and a news popularity score. The former is used to capture the personalized user interest in news. The latter is used to measure time-aware popularity of candidate news, which is predicted based on news content, recency, and real-time CTR using a unified framework. Besides, we propose a popularity-aware user encoder to eliminate the popularity bias in user behaviors for accurate interest modeling. Experiments on two real-world datasets show our method can effectively improve the accuracy and diversity for news recommendation.

PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity

False claims that have been previously fact-checked can still spread on social media. To mitigate their continual spread, detecting previously fact-checked claims is indispensable. Given a claim, existing works focus on providing evidence for detection by reranking candidate fact-checking articles (FC-articles) retrieved by BM25. However, these performances may be limited because they ignore the following characteristics of FC-articles: (1) claims are often quoted to describe the checked events, providing lexical information besides semantics; (2) sentence templates to introduce or debunk claims are common across articles, providing pattern information. Models that ignore the two aspects only leverage semantic relevance and may be misled by sentences that describe similar but irrelevant events. In this paper, we propose a novel reranker, MTM (Memory-enhanced Transformers for Matching) to rank FC-articles using key sentences selected with event (lexical and semantic) and pattern information. For event information, we propose a ROUGE-guided Transformer which is finetuned with regression of ROUGE. For pattern information, we generate pattern vectors for matching with sentences. By fusing event and pattern information, we select key sentences to represent an article and then predict if the article fact-checks the given claim using the claim, key sentences, and patterns. Experiments on two real-world datasets show that MTM outperforms existing methods. Human evaluation proves that MTM can capture key sentences for explanations.

Article Reranking by Memory-Enhanced Key Sentence Matching for Detecting Previously Fact-Checked Claims

Although deep neural networks have achieved prominent performance on many NLP tasks, they are vulnerable to adversarial examples. We propose Dirichlet Neighborhood Ensemble (DNE), a randomized method for training a robust model to defense synonym substitution-based attacks. During training, DNE forms virtual sentences by sampling embedding vectors for each word in an input sentence from a convex hull spanned by the word and its synonyms, and it augments them with the training data. In such a way, the model is robust to adversarial attacks while maintaining the performance on the original clean data. DNE is agnostic to the network architectures and scales to large models (e.g., BERT) for NLP applications. Through extensive experimentation, we demonstrate that our method consistently outperforms recently proposed defense methods by a significant margin across different network architectures and multiple data sets.

Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble

Increasing the input length has been a driver of progress in language modeling with transformers. We identify conditions where shorter inputs are not harmful, and achieve perplexity and efficiency improvements through two new methods that decrease input length.
First, we show that initially training a model on short subsequences before moving on to longer ones both reduces overall training time and, surprisingly, substantially improves perplexity.
Second, we show how to improve the efficiency of recurrence methods in transformers, which let models condition on previously processed tokens when generating sequences that exceed the maximal length the transformer can handle at once. Existing methods require computationally expensive relative position embeddings; we introduce a simple alternative of adding absolute position embeddings to queries and keys instead of to word embeddings, which efficiently produces superior results. We show that these recurrent models also benefit from short input lengths. 
Combining these techniques speeds up training by a factor of 1.65, reduces memory usage, and substantially improves perplexity on WikiText-103, without adding any parameters.

Shortformer: Better Language Modeling using Shorter Inputs

Task variance regularization, which can be used to improve the generalization of Multi-task Learning (MTL) models, remains unexplored in multi-task text classification. Accordingly, to fill this gap, this paper investigates how the task might be effectively regularized, and consequently proposes a multi-task learning method based on adversarial multi-armed bandit. The proposed method, named BanditMTL, regularizes the task variance by means of a mirror gradient ascent-descent algorithm. Adopting BanditMTL in the multi-task text classification context is found to achieve state-of-the-art performance. The results of extensive experiments back up our theoretical analysis and validate
the superiority of our proposals.

BanditMTL: Bandit-based Multi-task Learning for Text Classification

This paper describes a system proposed for the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies. We propose a Graph Rewriting based system for computing Enhanced Universal Dependencies, given the Basic Universal Dependencies. 


Graph Rewriting for Enhanced Universal Dependencies

We introduce our enhanced universal dependency parser with automated concatenation of embeddings and biaffine encoder.

Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings

This paper presents our multilingual dependency parsing system as used in the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies. Our system consists of an unfactorized biaffine classifier that operates directly on fine-tuned XLM-R embeddings and generates enhanced UD graphs by predicting the best dependency label (or absence of a dependency) for each pair of tokens. To avoid sparsity issues resulting from lexicalized dependency labels, we replace lexical items in relations with placeholders at training and prediction time, later retrieving them from the parse via a hybrid rule-based/machine-learning system. In addition, we utilize model ensembling at prediction time. Our system achieves high parsing accuracy on the blind test data, ranking 3rd out of 9 with an average ELAS F1 score of 86.97.

RobertNLP at the 2021 IWPT Shared Task: Simple Enhanced UD Parsing for 17 Languages

We present our contribution to the IWPT 2021 shared task on parsing into enhanced Universal Dependencies. Our main system component is a hybrid tree-graph parser that integrates (a) predictions of spanning trees for the enhanced graphs with (b) additional graph edges not present in the spanning trees. We also adopt a finetuning strategy where we first train a language-generic parser on the concatenation of treebanks from all available languages, and then, in a second step, finetune on each individual language separately. Additionally, we develop our own complete set of pre-processing modules relevant to the shared task, including tokenization, sentence segmentation, and multi-word token expansion, based on our own pre-training of character-level language models. Our submission reaches a macro-average ELAS of 89.24 on the test set. It ranks top among all teams, with a margin of more than 2 absolute ELAS over the next best-performing submission, and best score on 16 out of 17 languages.

TGIF: Tree-Graph Integrated-Format Parser for Enhanced UD with Two-Stage Generic- to Individual-Language Finetuning

We describe the DCU-EPFL submission to the IWPT 2021 Shared Task on Parsing into Enhanced Universal Dependencies. The task involves parsing Enhanced UD graphs, which are an extension of the basic dependency trees designed to be more facilitative towards representing semantic structure. Evaluation is carried out on 29 treebanks in 17 languages and participants are required to parse the data from each language starting from raw strings. Our approach uses the Stanza pipeline to preprocess the text files, XLM-RoBERTa to obtain contextualized token representations, and an edge-scoring and labeling model to predict the enhanced graph. Finally, we run a postprocessing script to ensure all of our outputs are valid Enhanced UD graphs. Our system places 6th out of 9 participants with a coarse Enhanced Labeled Attachment Score (ELAS) of 83.57.
We carry out additional post-deadline experiments which include using Trankit for pre-processing, XLM-RoBERTa-large, treebank concatenation, and multi-task learning. All of these modifications improve our initial score and our final system has an ELAS of 88.04.

Hi-Transformer: Hierarchical Interactive Transformer for Efficient and Effective Long Document Modeling

Downloads

Next from ACL-IJCNLP 2021

PP-Rec: News Recommendation with Personalized User Interest and Time-aware News Popularity

Similar lecture

PASS: Perturb-and-Select Summarizer for Product Reviews