Thailand

Fixed length summarization aims at generating summaries with a preset number of words or characters. Most recent researches incorporate length information with word embeddings as the input to the recurrent decoding unit, causing a compromise between length controllability and summary quality. In this work, we present an effective length controlling unit Length Attention (LenAtten) to break this trade-off. Experimental results show that LenAtten not only brings improvements in length controllability and ROGUE scores but also has great generalization ability. In the task of generating a summary with the target length, our model is 732 times better than the best-performing length controllable summarizer in length controllability on the CNN/Daily Mail dataset.

IJCNLP-AACL 2021

LenAtten: An Effective Length Controlling Unit For Text Summarization

controllable summarization

fixed length text summarization

attention mechanism

**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).

technical paper

Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied these shortcomings to beam search -- the de facto standard inference algorithm in NMT -- and Eikema & Aziz (2020) propose to use Minimum Bayes Risk (MBR) decoding on unbiased samples instead.

In this paper, we empirically investigate the properties of MBR decoding on a number of previously reported biases and failure cases of beam search. We find that MBR still exhibits a length and token frequency bias, owing to the MT metrics used as utility functions, but that MBR also increases robustness against copy noise in the training data and domain shift.

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

One of the reasons Transformer translation models are popular is that self-attention networks for context modelling can be easily parallelized at sequence level. However, the computational complexity of a self-attention network is $O(n^2)$, increasing quadratically with sequence length. By contrast, the complexity of LSTM-based approaches is only O(n). In practice, however, LSTMs are much slower to train than self-attention networks as they cannot be parallelized at sequence level: to model context, the current LSTM state relies on the full LSTM computation of the preceding state. This has to be computed n times for a sequence of length n. The linear transformations involved in the LSTM gate and state computations are the major cost factors in this. To enable sequence-level parallelization of LSTMs, we approximate full LSTM context modelling by computing hidden states and gates with the current input and a simple bag-of-words representation of the preceding tokens context. This allows us to compute each input step efficiently in parallel, avoiding the formerly costly sequential linear transformations. We then connect the outputs of each parallel step with computationally cheap element-wise computations. We call this the Highly Parallelized LSTM. To further constrain the number of LSTM parameters, we compute several small HPLSTMs in parallel like multi-head attention in the Transformer. The experiments show that our MHPLSTM decoder achieves significant BLEU improvements, while being even slightly faster than the self-attention network in training, and much faster than the standard LSTM.

Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation

Word alignment and machine translation are two closely related tasks. Neural translation models, such as RNN-based and Transformer models, employ a target-to-source attention mechanism which can provide rough word alignments, but with a rather low accuracy. High-quality word alignment can help
neural machine translation in many different ways, such as missing word detection, annotation transfer and lexicon injection. Existing methods for learning word alignment include statistical word aligners (e.g. GIZA++) and recently neural word alignment models. This paper presents a bidirectional Transformer based alignment (BTBA) model for unsupervised learning of the word alignment task. Our BTBA model predicts the current target word by attending the source context and both left-side and right-side target context to produce accurate target-to-source attention (alignment). We further fine-tune the target-to-source attention in the BTBA model to obtain better alignments using a full context based optimization
method and self-supervised training. We test our method on three word alignment tasks and show that our method outperforms both previous neural word alignment approaches and the popular statistical word aligner GIZA++.

A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment

Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradationon rich-resource language pairs. We attribute this degeneration to parameter interference. In this paper, we propose LaSS to jointly train a single unified multilingual MT model. LaSS learns Language Specific Sub-network (LaSS) for each language pair to counter parameter interference. Comprehensive experiments on IWSLT and WMT datasets with various Transformer architectures show that LaSS obtains gains on 36 language pairs by up to 1.2 BLEU. Besides, LaSS shows its strong generalization performance at easy adaptation to new language pairs and zero-shot translation. LaSS boosts zero-shot translation with an average of 8.3 BLEU on 30 language pairs. Codes and trained models are available at https://github.com/NLP-Playground/LaSS.

Learning Language Specific Sub-network for Multilingual Machine Translation

The high-quality translation results produced by machine translation (MT) systems still pose a huge challenge for automatic evaluation. Current MT evaluation pays the same attention to each sentence component, while the questions of real-world examinations (e.g., university examinations) have different difficulties and weightings. In this paper, we propose a novel difficulty-aware MT evaluation metric, expanding the evaluation dimension by taking translation difficulty into consideration. A translation that fails to be predicted by most MT systems will be treated as a difficult one and assigned a large weight in the final score function, and conversely. Experimental results on the WMT19 English-German Metrics shared tasks show that our proposed method outperforms commonly used MT metrics in terms of human correlation. In particular, our proposed method performs well even when all the MT systems are very competitive, which is when most existing metrics fail to distinguish between them. The source code is freely available at https://github.com/NLP2CT/Difficulty-Aware-MT-Evaluation.

Difficulty-Aware Machine Translation Evaluation

Transfer learning has become the dominant paradigm for many natural language processing tasks. In addition to models being pretrained on large datasets, they can be further trained on intermediate (supervised) tasks that are similar to the target task. For small Natural Language Inference (NLI) datasets, language modelling is typically followed by pretraining on a large (labelled) NLI dataset before fine-tuning with each NLI subtask.
In this work, we explore Gradient Boosted Decision Trees (GBDTs) as an alternative to the commonly used Multi-Layer Perceptron (MLP) classification head. GBDTs have desirable properties such as good performance on dense, numerical features and are effective where the ratio of the number of samples w.r.t the number of features is low.
In addition, we introduce FreeGBDT, a method of fitting a GBDT head on the features computed during fine-tuning to increase performance without additional computation by the neural network. We demonstrate the effectiveness of our method on several NLI datasets using a strong baseline model (RoBERTa-large with MNLI pretraining). The FreeGBDT shows a consistent improvement over the standard MLP classification head.

Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning

Despite recent advances, standard sequence labeling systems often fail when processing noisy user-generated text or consuming the output of an Optical Character Recognition (OCR) process. In this paper, we improve the noise-aware training method by proposing an empirical error generation approach that employs a sequence-to-sequence model trained to perform translation from error-free to erroneous text. Using an OCR engine, we generated a large parallel text corpus for training and produced several real-world noisy sequence labeling benchmarks for evaluation. Moreover, to overcome the data sparsity problem that exacerbates in the case of imperfect textual input, we learned noisy language model-based embeddings. Our approach outperformed the baseline noise generation and error correction techniques on the erroneous sequence labeling data sets. To facilitate future research on robustness, we make our code, embeddings, and data conversion scripts publicly available.

Empirical Error Modeling Improves Robustness of Noisy Neural Sequence Labeling

Information Extraction (IE) for semi-structured document images is often approached as a sequence tagging problem by classifying each recognized input token into one of the IOB (Inside, Outside, and Beginning) categories. 
However, such problem setup has two inherent limitations that (1) it cannot easily handle complex spatial relationships and (2) it is not suitable for highly structured information, which are nevertheless frequently observed in real-world document images. 
To tackle these issues, we first formulate the IE task as spatial dependency parsing problem that focuses on the relationship among text tokens in the documents.
Under this setup, we then propose SPADE (SPAtial DEpendency parser) that models highly complex spatial relationships and an arbitrary number of information layers in the documents in an end-to-end manner.
We evaluate it on various kinds of documents such as receipts, name cards, forms, and invoices, and show that it achieves a similar or better performance compared to strong baselines including BERT-based IOB taggger.

Spatial Dependency Parsing for Semi-Structured Document Information Extraction

Current open-domain question answering systems often follow a Retriever-Reader architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer.
In this paper, we propose a simple and effective passage reranking method, named Reader-guIDEd Reranker (RIDER), which does not involve training and reranks the retrieved passages solely based on the top predictions of the reader before reranking.
We show that RIDER, despite its simplicity, achieves 10 to 20 absolute gains in top-1 retrieval accuracy and 1 to 4 Exact Match (EM) gains without refining the retriever or reader.
In addition, RIDER, without any training, outperforms state-of-the-art transformer-based supervised rerankers.
Remarkably, RIDER achieves 48.3 EM on the Natural Questions dataset and 66.4 EM on the TriviaQA dataset when only 1,024 tokens (7.8 passages on average) are used as the reader input after passage reranking.

Reader-Guided Passage Reranking for Open-Domain Question Answering

Entities and their mentions convey significant semantic information in documents. In multi-document summarization, the same entity may appear across different documents. Capturing such cross-document entity information can be beneficial -- intuitively, it allows the system to aggregate diverse useful information around the same entity for better summarization. In this paper, we present EMSum, an entity-aware model for abstractive multi-document summarization. Our model augments the classical Transformer-based encoder-decoder framework with a heterogeneous graph consisting of text units and entities as nodes, which allows rich cross-document information to be captured. In the decoding process, we design a novel two-level attention mechanism, allowing the model to deal with saliency and redundancy issues explicitly. Our model can also be used together with pre-trained language models, arriving at improved performance. We conduct comprehensive experiments on the standard datasets and the results show the effectiveness of our approach.

LenAtten: An Effective Length Controlling Unit For Text Summarization

Downloads

Next from IJCNLP-AACL 2021

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

Similar lecture

MA-BERT: Learning Representation by Incorporating Multi-Attribute Knowledge in Transformers

LenAtten: An Effective Length Controlling Unit For Text Summarization

.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

Understanding the Properties of Minimum Bayes Risk Decoding in Neural Machine Translation

Similar lecture

MA-BERT: Learning Representation by Incorporating Multi-Attribute Knowledge in Transformers

Downloads