Thailand

In the era of pre-trained language models, Transformers are the de facto choice of model architectures. While recent research has shown promise in entirely convolutional, or CNN, architectures, they have not been explored using the pre-train-fine-tune paradigm. In the context of language models, are convolutional models competitive to Transformers when pre-trained? This paper investigates this research question and presents several interesting findings. Across an extensive set of experiments on 8 datasets/tasks, we find that CNN-based pre-trained models are competitive and outperform their Transformer counterpart in certain scenarios, albeit with caveats. Overall, the findings outlined in this paper suggest that conflating pre-training and architectural advances is misguided and that both advances should be considered independently. We believe our research paves the way for a healthy amount of optimism in alternative architectures.

IJCNLP-AACL 2021

Are Pretrained Convolutions Better than Pretrained Transformers?

convolutions

pretraining

transformers

**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

Technology for language generation has advanced rapidly, spurred by advancements in pre-training large models on massive amounts of data and the need for intelligent agents to communicate in a natural manner. While techniques can effectively generate fluent text, they can also produce undesirable societal biases that can have a disproportionately negative impact on marginalized populations. Language generation presents unique challenges for biases in terms of direct user interaction and the structure of decoding techniques. To better understand these challenges, we present a survey on societal biases in language generation, focusing on how data and techniques contribute to biases and progress towards reducing biases. Motivated by a lack of studies on biases from decoding techniques, we also conduct experiments to quantify the effects of these techniques. By further discussing general trends and open challenges, we call to attention promising directions for research and the importance of fairness and inclusivity considerations for language generation applications.

Societal Biases in Language Generation: Progress and Challenges

We demonstrate that transformers obtain impressive performance even when some of the layers are randomly initialized and never updated. Inspired by old and well-established ideas in machine learning, we explore a variety of non-linear “reservoir” layers interspersed with regular transformer layers, and show improvements in wall-clock compute time until convergence, as well as overall performance, on various machine translation and (masked) language modelling tasks.

Reservoir Transformers

Active Learning (AL) has been successfully applied to Deep Learning in order to drastically reduce the amount of data required to achieve high performance. Previous works have shown that lightweight architectures for Named Entity Recognition (NER) can achieve optimal performance with only 25% of the original training data. However, these methods do not exploit the sequential nature of language and the heterogeneity of uncertainty within each instance, requiring the labelling of whole sentences. Additionally, this standard method requires that the annotator has access to the full sentence when labelling. In this work, we overcome these limitations by allowing the AL algorithm to query subsequences within sentences, and propagate their labels to other sentences. We achieve highly efficient results on OntoNotes 5.0, only requiring 13% of the original training data, and CoNLL 2003, requiring only 27%. This is an improvement of 39% and 37% compared to querying full sentences.

Subsequence Based Deep Active Learning for Named Entity Recognition

The rapid development of large pre-trained language models has greatly increased the demand for model compression techniques, among which quantization is a popular solution. In this paper, we propose BinaryBERT, which pushes BERT quantization to the limit by weight binarization. We find that a binary BERT is hard to be trained directly than a ternary counterpart due to its complex and irregular loss landscape. Therefore, we propose ternary weight splitting, which initializes BinaryBERT by equivalently splitting from a half-sized ternary network. The binary model thus inherits the good performance of the ternary one, and can be further enhanced by fine-tuning the new architecture after splitting. Empirical results show that our BinaryBERT has only a slight performance drop compared with the full-precision model while being 24x smaller, achieving the state-of-the-art compression results on the GLUE and SQuAD benchmarks. Code will be released.

BinaryBERT: Pushing the Limit of BERT Quantization

We propose an effective context-sensitive neural model for time to event (TTE) prediction task, which aims to predict the amount of time to/from the occurrence of given events in streaming content. We investigate this problem in the context of a multi-task learning framework, which we enrich with time difference embeddings. In addition, we develop a multi-genre dataset of English events about soccer competitions and academy awards ceremonies, and their relevant tweets obtained from Twitter. Our model is 1.4 and 3.3 hours more accurate than the current state-of-the-art model in estimating TTE on English and Dutch tweets respectively. We examine different aspects of our model to illustrate its source of improvement.

Embedding Time Differences in Context-sensitive Neural Networks for Learning Time to Event

Forming and interpreting abstraction is a core process in human communication. In particular, when giving and performing complex instructions stated in natural language (NL), people may naturally evoke abstract constructs such as objects, loops, conditions and functions to convey their intentions in an efficient and precise way. Yet, interpreting and grounding abstraction stated in NL has not been systematically studied in NLP/AI. To elicit naturally-occurring abstractions in NL we develop the Hexagons referential game, where players describe increasingly complex images on a two-dimensional Hexagons board, and other players need to follow these instructions to recreate the images. Using this game we collected the Hexagons dataset, which consists of 164 images and over 3000 naturally-occurring instructions, rich with diverse abstractions. Results of our baseline models on an instruction-to-execution task derived from the Hexagons dataset confirm that higher-level abstractions in NL are indeed more challenging for current systems to process. Thus, this dataset exposes a new and challenging dimension for grounded semantic parsing, and we propose it for the community as a future benchmark to explore more sophisticated and high-level communication within NLP applications.

Draw Me a Flower: Grounding Abstract Structures in Executable Instructions

Code summarization and generation empower conversion between programming language(PL) and natural language (NL), while code translation avails the migration of legacy code from one PL to another. This paper introduces PLBART, a sequence-to-sequence model capable of performing a broad spectrum of program and language understanding and generation tasks. PLBART is pre-trained on an extensive collection of Java and Python functions and associated NL text via denoising autoencoding. Experiments on code summarization in the English language, code generation, and code translation in seven programming languages show that PLBART outperforms or rivals state-of-the-art models. Moreover, experiments on discriminative tasks,e.g., program repair, clone detection, and vulnerable code detection, demonstrate PLBART’s effectiveness in program understanding. Furthermore, analysis reveals that PLBART learns program syntax, style (e.g., identifier naming convention), logical flow (e.g., if block inside an else block is equivalent to else if block) that are crucial to program semantics and thus ex-cels even with limited annotations.

Unified Pre-training for Program Understanding and Generation

Decompiling binary executables to high-level code is an important step in reverse engineering scenarios, such as malware analysis and legacy code maintenance. However, the generated high-level code is difficult to understand since the original variable names are lost. In this paper, we leverage transformer models to reconstruct the original variable names from decompiled code. Inherent differences between code and natural language present certain challenges in applying conventional transformer-based architectures to variable name recovery. We propose DIRECT, a novel transformer-based architecture customized specifically for the task at hand. We evaluate our model on a dataset of decompiled functions and find that DIRECT outperforms the previous state-of-the-art model by up to 20%. We also present ablation studies evaluating the impact of each of our modifications. We make the source code of DIRECT available to encourage reproducible research.

DIRECT : A Transformer-based Model for Decompiled Identifier Renaming

Answering a programming question with only its title is difficult as salient contextual information is left out. To address this, we present a corpus of over 40,000 StackOverflow question texts to be used in conjunction with the corresponding intents from the CoNaLa dataset (Yin et al., 2018). Using both the intent and the question body, we use BART to establish a baseline BLEU score of 34.35 for this new task. We then find further improvements of 2.8% by combining the mined CoNaLa data with the labeled data to achieve a 35.32 BLEU score. We then evaluate the prior state-of-the-art CoNaLa models with this additional data. We find that our proposed method of using the body and mined data beats that of the previous state-of-the-art by a 71.96% BLEU score. Finally, we perform ablations that prove that BART is an unsupervised multimodal learner and examine its extractive behavior.

Reading StackOverflow Encourages Cheating: Adding Question Text Improves Extractive Code Generation

A key challenge in human-machine communication is expressing one's intent using precise programmatic concepts. 
This process can be unintuitive, as users are forced to adapt to the idiosyncratic expressions chosen by the system architect. 
We suggest an \emph{adaptive alignment} approach that allows a system to gradually align its representation of underlying programmatic concepts, expressed in program transformations, with the conventions used by a community of users to express concepts in natural language.
Specifically, we cast the problem of alignment as an online inference problem, aiming to recover the ground-truth conventions shared within a community of users from a dataset of interactions with users. 
We present a series of simulations and an interactive user study using a subset of the \texttt{matplotlib} domain. 
We find that a community of users can quickly ``naturalize'' the obscure underlying programmatic transformations, allowing subsequent users to use the system more efficiently.

Are Pretrained Convolutions Better than Pretrained Transformers?

Downloads

Next from IJCNLP-AACL 2021

Societal Biases in Language Generation: Progress and Challenges

Similar lecture

Reservoir Transformers