Ireland

In many natural language processing (NLP) tasks the same input (e.g. source sentence) can have multiple possible outputs (e.g. translations). To analyze how this ambiguity (also known as intrinsic uncertainty) shapes the distribution learned by neural sequence models we measure sentence-level uncertainty by computing the degree of overlap between references in multi-reference test sets from two different NLP tasks: machine translation (MT) and grammatical error correction (GEC). At both the sentence- and the task-level, intrinsic uncertainty has major implications for various aspects of search such as the inductive biases in beam search and the complexity of exact search. In particular, we show that well-known
pathologies such as a high number of beam search errors, the inadequacy of the mode, and the drop in system performance with large beam sizes apply to tasks with high level of ambiguity such as MT but not to less uncertain tasks such as GEC. Furthermore, we propose a novel exact n-best search algorithm for neural sequence models, and show that intrinsic uncertainty affects model uncertainty as the model tends to overly spread out the probability mass for uncertain tasks and sentences.

ACL 2022

Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models

intrinsic uncertainty

sequence-to-sequence

beam search

# Welcome everyone to ACL 2022!

The 60th Annual Meeting of the Association for Computational Linguistics is taking place May 22-27, 2022 as a hybrid event, in Dublin and online. We are happy to welcome all of you to this anniversary edition with an almost 50-50 in-person and virtual participation. 
The main conference program features oral presentations, in-person and virtual posters and demo sessions, a plenary session for our best paper presentations and awards, three amazing keynote events and two new initiatives of invited talks: Spotlight Talks for Young Rising Stars (STIRS) and The Next Big Idea Talks. Posters (including Findings of ACL 2022) and demos are grouped by areas for both the in-person and the virtual sessions. For the virtual component, the talks will be on Zoom and the posters and the demos will be in GatherTown. The Student Research Workshop will have an oral session and a poster session as part of Poster Session 1. The program also features eight Tutorials and 28 Workshops. 

 
We wish you a wonderful conference! 
[**The ACL 2022 Organizing Committee**](https://www.2022.aclweb.org/organisers)
 
[**Conference Handbook**](https://drive.google.com/file/d/1_BUCMfhMVrjG9E2e71aHdHeE28KSje0l/view?usp=sharing) 
[**Mini Handbook**](https://drive.google.com/file/d/1qlBKl0wzmlVF1oCeMQl3BahLd9nLP5Ce/view?usp=sharing) 
[**Posters and Demo guides**](https://drive.google.com/file/d/1UucMAoCNncIOaH1rMMDa0owuG9qgvJTG/view?usp=sharing)

The Association for Computational Linguistics (ACL) is the premier international scientific and professional society for people working on computational problems involving human language, a field often referred to as either computational linguistics or natural language processing (NLP). 

poster

In the domain of Morphology, Inflection is a fundamental and important task that gained a lot of traction in recent years, mostly via SIGMORPHON's shared-tasks. With average accuracy above 0.9 over the scores of all languages, the task is considered mostly solved using relatively generic neural seq2seq models, even with little data provided. In this work, we propose to re-evaluate morphological inflection models by employing harder train-test splits that will challenge the generalization capacity of the models. In particular, as opposed to the na{ï}ve split-by-form, we propose a split-by-lemma method to challenge the performance on existing benchmarks. Our experiments with the three top-ranked systems on the SIGMORPHON's 2020 shared-task show that the lemma-split presents an average drop of 30 percentage points in macro-average for the 90 languages included. The effect is most significant for low-resourced languages with a drop as high as 95 points, but even high-resourced languages lose about 10 points on average. Our results clearly show that generalizing inflection to unseen lemmas is far from being solved, presenting a simple yet effective means to promote more sophisticated models.

(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models’ Performance

Evaluation of open-domain dialogue systems is highly challenging and development of better techniques is highlighted time and again as desperately needed. Despite substantial efforts to carry out reliable live evaluation of systems in recent competitions, annotations have been abandoned and reported as too unreliable to yield sensible results. This is a serious problem since automatic metrics are not known to provide a good indication of what may or may not be a high-quality conversation. Answering the distress call of competitions that have emphasized the urgent need for better evaluation techniques in dialogue, we present the successful development of human evaluation that is highly reliable while still remaining feasible and low cost. Self-replication experiments reveal almost perfectly repeatable results with a correlation of $r=0.969$. Furthermore, due to the lack of appropriate methods of statistical significance testing, the likelihood of potential improvements to systems occurring due to chance is rarely taken into account in dialogue evaluation, and the evaluation we propose facilitates application of standard tests. Since we have developed a highly reliable evaluation method, new insights into system performance can be revealed. We therefore include a comparison of state-of-the-art models (i) with and without personas, to measure the contribution of personas to conversation quality, as well as (ii) prescribed versus freely chosen topics. Interestingly with respect to personas, results indicate that personas do not positively contribute to conversation quality as expected.

Achieving Reliable Human Assessment of Open-Domain Dialogue Systems

In this paper, we propose an entity-based neural local coherence model which is linguistically more sound than previously proposed neural coherence models. Recent neural coherence models encode the input document using large-scale pretrained language models. Hence their basis for computing local coherence are words and even sub-words. An analysis of their output shows that these models frequently compute coherence on the basis of connections between (sub-)words which, from a linguistic perspective, should not play a role. Still, these models achieve state-of-the-art performance in several end applications. In contrast to these models, we compute coherence on the basis of entities by constraining the input to noun phrases and proper names. This provides us with an explicit representation of the most important items in sentences leading to the notion of focus. This brings our model linguistically in line with pre-neural models of computing coherence. It also gives us better insight into the behaviour of the model thus leading to better explainability. Our approach is also in accord with a recent study (O'Connor and Andreas, 2021), which shows that most usable information is captured by nouns and verbs in transformer-based language models. We evaluate our model on three downstream tasks showing that it is not only linguistically more sound than previous models but also that it outperforms them in end applications.

Entity-based Neural Local Coherence Modeling

Several high-profile events, such as the mass testing of emotion recognition systems on vulnerable sub-populations and using question answering systems to make moral judgments, have highlighted how technology will often lead to more adverse outcomes for those that are already marginalized. At issue here are not just individual systems and datasets, but also the AI tasks themselves. In this position paper, I make a case for thinking about ethical considerations not just at the level of individual models and datasets, but also at the level of AI tasks. I will present a new form of such an effort, Ethics Sheets for AI Tasks, dedicated to fleshing out the assumptions and ethical considerations hidden in how a task is commonly framed and in the choices we make regarding the data, method, and evaluation. I will also present a template for ethics sheets with 50 ethical considerations, using the task of emotion recognition as a running example. Ethics sheets are a mechanism to engage with and document ethical considerations before building datasets and systems. Similar to survey articles, a small number of ethics sheets can serve numerous researchers and developers.

Ethics Sheets for AI Tasks

We introduce BitFit, a sparse-finetuning method where only the bias-terms of the model (or a subset of them) are being modified. We show that with small-to-medium training data, applying BitFit on pre-trained BERT models is competitive with (and sometimes better than) fine-tuning the entire model. For larger data, the method is competitive with other sparse fine-tuning methods.
Besides their practical utility, these findings are relevant for the question of understanding the commonly-used process of finetuning: they support the hypothesis that finetuning is mainly about exposing knowledge induced by language-modeling training, rather than learning new task-specific linguistic knowledge.

BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models

Interpolation-based regularisation methods such as Mixup, which generate virtual training samples, have proven to be effective for various tasks and modalities. We extend Mixup and propose DMIX, an adaptive distance aware interpolative Mixup that selects samples based on their diversity in the embedding space. DMIX leverages the hyperbolic space as a similarity measure among input samples for a richer encoded representation. DMIX achieves state-of-the-art results on sentence classification over existing data augmentation methods on 8 benchmark datasets across English, Arabic, Turkish, and Hindi languages while achieving benchmark F1 scores in 3 times less number of iterations. We probe the effectiveness of DMIX in conjunction with various similarity measures and qualitatively analyze the different components. DMIX being generalizable, can be applied to various tasks, models and modalities.

DMix: Adaptive Distance-aware Interpolative Mixup

GPT is an auto-regressive Transformer-based pre-trained language model which has attracted a lot of attention in the natural language processing (NLP) domain. The success of GPT is mostly attributed to its pre-training on huge amount of data and its large number of parameters. Despite the superior performance of GPT, this overparameterized nature of GPT can be very prohibitive for deploying this model on devices with limited computational power or memory. This problem can be mitigated using model compression techniques; however, compressing GPT models has not been investigated much in the literature. In this work, we use Kronecker decomposition to compress the linear mappings of the GPT-2 model. Our Kronecker
GPT-2 model (KnGPT2) is initialized based on the Kronecker decomposed version of the GPT2 model and then is undergone a very light pretraining on only a small portion of the training data with intermediate layer knowledge distillation (ILKD). Finally, our KnGPT2 is fine-tuned on downstream tasks using ILKD as well. We evaluate our model on both language modeling and General Language Understanding Evaluation benchmark tasks and show that with more efficient pre training and similar number of parameters, our KnGPT2 outperforms the existing DistilGPT2 model significantly.

Kronecker Decomposition for GPT Compression

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While offering unmatched retrieval performance, such models: 1) are typically pretrained from scratch and thus less scalable, 2) suffer from huge retrieval latency and inefficiency issues, which makes them impractical in realistic applications. To address these crucial gaps towards both improved and efficient cross-modal retrieval, we propose a novel fine-tuning framework that turns any pretrained text-image multi-modal model into an efficient retrieval model. The framework is based on a cooperative retrieve-and-rerank approach which combines: 1)}twin networks (i.e., a bi-encoder) to separately encode all items of a corpus, enabling efficient initial retrieval, and 2) a cross-encoder component for a more nuanced (i.e., smarter) ranking of the retrieved small set of items. We also propose to jointly fine-tune the two components with shared weights, yielding a more parameter-efficient model. Our experiments on a series of standard cross-modal retrieval benchmarks in monolingual, multilingual, and zero-shot setups, demonstrate improved accuracy and huge efficiency benefits over the state-of-the-art cross-encoders.

Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval

Tuning pre-trained language models (PLMs) with task-specific prompts has been a promising approach for text classification. Particularly, previous studies suggest that prompt-tuning has remarkable superiority in the low-data scenario over the generic fine-tuning methods with extra classifiers. The core idea of prompt-tuning is to insert text pieces, i.e., template, to the input and transform a classification problem into a masked language modeling problem, where a crucial step is to construct a projection, i.e., verbalizer, between a label space and a label word space. A verbalizer is usually handcrafted or searched by gradient descent, which may lack coverage and bring considerable bias and high variances to the results. In this work, we focus on incorporating external knowledge into the verbalizer, forming a knowledgeable prompt-tuning (KPT), to improve and stabilize prompt-tuning. Specifically, we expand the label word space of the verbalizer using external knowledge bases (KBs) and refine the expanded label word space with the PLM itself before predicting with the expanded label word space. Extensive experiments on zero and few-shot text classification tasks demonstrate the effectiveness of knowledgeable prompt-tuning.

Knowledgeable Prompt-tuning: Incorporating Knowledge into Prompt Verbalizer for Text Classification

Transformer-based models are widely used in natural language understanding (NLU) tasks, and multimodal transformers have been effective in visual-language tasks. This study explores distilling visual information from pretrained multimodal transformers to pretrained language encoders. Our framework is inspired by cross-modal encoders' success in visual-language tasks while we alter the learning objective to cater to the language-heavy characteristics of NLU. After training with a small number of extra adapting steps and finetuned, the proposed XDBERT (cross-modal distilled BERT) outperforms pretrained-BERT in general language understanding evaluation (GLUE), situations with adversarial generations (SWAG) benchmarks, and readability benchmarks. We analyze the performance of XDBERT on GLUE to show that the improvement is likely visually grounded.

Uncertainty Determines the Adequacy of the Mode and the Tractability of Decoding in Sequence-to-Sequence Models

Downloads

Next from ACL 2022

(Un)solving Morphological Inflection: Lemma Overlap Artificially Inflates Models’ Performance

Similar lecture

Coloring the Blank Slate: Pre-training Imparts a Hierarchical Inductive Bias to Sequence-to-sequence Models

Stay up to date with the latest Underline news!

PRESENTATIONS

CONFERENCES

COMPANY

RESOURCES