Thailand

Pre-trained text-to-text transformers such as BART have achieved impressive performance across a range of NLP tasks. Recent study further shows that they can learn to generalize to novel tasks, by including task descriptions as part of the source sequence and training the model with (source, target) examples. At test time, these fine-tuned models can make inferences on new tasks using the new task descriptions as part of the input. However, this approach has potential limitations, as the model learns to solve individual (source, target) examples (i.e., at the instance level), instead of learning to solve tasks by taking all examples within a task as a whole (i.e., at the task level). To this end, we introduce Hypter, a framework that improves text-to-text transformer&#39;s generalization ability to unseen tasks by training a hypernetwork to generate task-specific, light-weight adapters from task descriptions. Experiments on ZEST dataset and a synthetic SQuAD dataset demonstrate that Hypter improves upon fine-tuning baselines. Notably, when using BART-Large as the main network, Hypter brings 11.3% comparative improvement on ZEST dataset.

ACL 2021

Learning to Generate Task-Specific Adapters from Task Description

text-to-text transformer

adapter

zero-shot learning

**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). 

This Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) was to be held in Bangkok, Thailand, during August 1-6, 2021 and is now virtual on the Underline platform.

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

Pre-trained text-to-text transformers such as BART have achieved impressive performance across a range of NLP tasks. Recent study further shows that they can learn to generalize to novel tasks, by including task descriptions as part of the source sequence and training the model with (source, target) examples. At test time, these fine-tuned models can make inferences on new tasks using the new task descriptions as part of the input. However, this approach has potential limitations, as the model learns to solve individual (source, target) examples (i.e., at the instance level), instead of learning to solve tasks by taking all examples within a task as a whole (i.e., at the task level). To this end, we introduce Hypter, a framework that improves text-to-text transformer's generalization ability to unseen tasks by training a hypernetwork to generate task-specific, light-weight adapters from task descriptions. Experiments on ZEST dataset and a synthetic SQuAD dataset demonstrate that Hypter improves upon fine-tuning baselines. Notably, when using BART-Large as the main network, Hypter brings 11.3% comparative improvement on ZEST dataset.

poster

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

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.

Are Pretrained Convolutions Better than Pretrained Transformers?

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.

Community Driven Alignment of Natural and Programming Languages

A great part of software development involves conceptualizing or communicating the underlying procedures and logic that needs to be expressed in programs. One major difficulty of programming is turning concept into code, especially when dealing with the APIs of unfamiliar libraries. Recently, there has been a proliferation of machine learning methods for code generation and retrieval from natural language queries, but these have primarily been evaluated purely based on retrieval accuracy or overlap of generated code with developer written code, and the actual effect of these methods on the developer workflow is surprisingly unattested. In this paper, we perform the first comprehensive investigation of the promise and challenges of using such technology inside the PyCharm IDE, asking “at the current state of technology does it improve developer productivity or accuracy, how does it affect the developer experience, and what are the remaining gaps and challenges?” To facilitate the study, we first develop a plugin for the PyCharm IDE that implements a hybrid of code generation and code retrieval functionality, and orchestrate virtual environments to enable collection of many user events (e.g. web browsing, keystrokes, fine-grained code edits). We ask developers with various backgrounds to complete 7 varieties of 14 Python programming tasks ranging from basic file manipulation to machine learning or data visualization, with or without the help of the plugin. While qualitative surveys of developer experience are largely positive, quantitative results with regards to increased productivity, code
quality, or program correctness are inconclusive. Further analysis identifies several pain points that could
improve the effectiveness of future machine learning based code generation/retrieval developer assistants, and demonstrates when developers prefer code generation over code retrieval and vice versa. We release all data and software to pave the road for future empirical studies on this topic, as well as development of better code generation models.

In-IDE Code Generation from Natural Language: Promise and Challenges

Analysis of teacher evaluations is crucial to the development of robust educational programs, particularly through the validation of desirable qualities being reflected on in the text. This research applies Natural Language Processing techniques on a real-world dataset from a Filipino education non-profit to explore insights from analyzing evaluations written by Teacher Fellows who assess their own progress. Prior to this research, only qualitative assessment had been conducted on the text. Inspired by the use of word embedding similarities to capture semantic alignment, we utilize GloVe embeddings to determine to what extent these evaluations reflect concepts critical to measuring the competency of Teacher Fellows and upholding the organization’s Vision and Mission. As Fellows’ quantitative ratings improved, so too did their demonstration of competency in the text. Further, Teacher Fellow language was consistent with the organization’s Vision and Mission. This research therefore showcases the possibilities of NLP in education, improving our understanding of Teacher Fellow evaluations, which can lead to advances in program operations and education efforts.

Using Word Embeddings to Analyze Teacher Evaluations: An Application to a Filipino Education Non-Profit Organization

Conversational Agents (CAs) can be a proxy for disseminating information and providing support to the public, especially in times of crisis. CAs can scale to reach larger numbers of end-users than human operators, while they can offer information interactively and engagingly. In this work, we present Theano, a Greek-speaking virtual assistant for COVID-19. Theano presents users with COVID-19 statistics and facts and informs users about the best health practices as well as the latest COVID-19 related guidelines. Additionally, Theano provides support to end-users by helping them self-assess their symptoms and redirecting them to first-line health workers. The relevant, localized information that Theano provides, makes it a valuable tool for combating COVID-19 in Greece. Theano has already conversed with different users in more than 170 different conversations through a web interface as a chatbot and over the phone as a voice bot.

Learning to Generate Task-Specific Adapters from Task Description

Downloads

Next from ACL 2021

Subsequence Based Deep Active Learning for Named Entity Recognition

Similar lecture

On the Effectiveness of Adapter-based Tuning for Pretrained Language Model Adaptation

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES