Croatia

Real-world applications of neural language models often involve running many different models over the same corpus. The high computational cost of these runs has led to interest in techniques that can reuse the contextualized embeddings produced in previous runs to speed training and inference of future ones. We refer to this approach as embedding recycling (ER). While multiple ER techniques have been proposed, their practical effectiveness is still unknown because existing evaluations consider very few models and do not adequately account for overhead costs. We perform an extensive evaluation of ER across eight different models (17 to 900 million parameters) and fourteen tasks in English. We show how a simple ER technique that caches activations from an intermediate layer of a pretrained model, and learns task-specific adapters on the later layers, is broadly effective. For the best-performing baseline in our experiments (DeBERTa-v2 XL), adding a precomputed cache results in a &gt;90% speedup during training and 87-91% speedup for inference, with negligible impact on accuracy. Our analysis reveals important areas of future work.

EACL 2023

Embedding Recycling for Language Models

efficient nlp

green nlp

Real-world applications of neural language models often involve running many different models over the same corpus. The high computational cost of these runs has led to interest in techniques that can reuse the contextualized embeddings produced in previous runs to speed training and inference of future ones. We refer to this approach as embedding recycling (ER). While multiple ER techniques have been proposed, their practical effectiveness is still unknown because existing evaluations consider very few models and do not adequately account for overhead costs. We perform an extensive evaluation of ER across eight different models (17 to 900 million parameters) and fourteen tasks in English. We show how a simple ER technique that caches activations from an intermediate layer of a pretrained model, and learns task-specific adapters on the later layers, is broadly effective. For the best-performing baseline in our experiments (DeBERTa-v2 XL), adding a precomputed cache results in a >90% speedup during training and 87-91% speedup for inference, with negligible impact on accuracy. Our analysis reveals important areas of future work.

findings / work in progress

### Welcome to the 17th Conference of the European Chapter of the Association for Computational Linguistics (EACL) 
Continuing its mission of expanding and involving the science community of all European countries, EACL had selected the Ukrainian community for the 16th EACL, which took place online due to the COVID pandemic. Unfortunately, the ongoing war made the organisation in Kyiv impossible. Considering the importance of physical interaction among researchers, especially after the restrictions imposed by the COVID pandemic, in addition to an online mode, the conference will be held in Dubrovnik, Croatia, from 2 to 6 of May, 2023. The original aim of strengthening the connection with the Ukrainian community will not change as our program will feature a dedicated session and a workshop to highlight work on Ukrainian language technologies. As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

You need to register for the conference in order to access this site. Please visit https://2023.eacl.org/registration for more information.

As the flagship European conference in the field of computational linguistics, EACL welcomes European and international researchers covering a broad spectrum of research areas that are concerned with computational approaches to natural language.

While modern masked language models (LMs) are trained on ever larger corpora, we here explore the effects of down-scaling training to a modestly-sized but representative, well-balanced, and publicly available English text source -- the British National Corpus. We show that pre-training on this carefully curated corpus can reach better performance than the original BERT model. We argue that this type of corpora has great potential as a language modeling benchmark. To showcase this potential, we present fair, reproducible and data-efficient comparative studies of LMs, in which we evaluate several training objectives and model architectures and replicate previous empirical results in a systematic way. We propose an optimized LM architecture called LTG-BERT.

Trained on 100 million words and still in shape: BERT meets British National Corpus

Training end-to-end speech translation (ST) systems requires sufficiently large-scale data, which is unavailable for most language pairs and domains. One practical solution to the data scarcity issue is to convert text-based machine translation (MT) data to ST data via text-to-speech (TTS) systems.Yet, using TTS systems can be tedious and slow. In this work, we propose SpokenVocab, a simple, scalable and effective data augmentation technique to convert MT data to ST data on-the-fly. The idea is to retrieve and stitch audio snippets, corresponding to words in an MT sentence, from a spoken vocabulary bank. Our experiments on multiple language pairs show that stitched speech helps to improve translation quality by an average of 1.83 BLEU score, while performing equally well as TTS-generated speech in improving translation quality. We also showcase how SpokenVocab can be applied in code-switching ST for which often no TTS systems exit.

Generating Synthetic Speech from SpokenVocab for Speech Translation

The limits of open-ended generative models are unclear, yet increasingly important. What causes them to succeed and what causes them to fail? In this paper, we take a prompt-centric approach to analyzing and bounding the abilities of open-ended generative models. We present a generic methodology of analysis with two challenging prompt constraint types: structural and stylistic. These constraint types are categorized into a set of well-defined constraints that are analyzable by a single prompt. We then systematically create a diverse set of simple, natural, and useful prompts to robustly analyze each individual constraint. Using the GPT-3 text-davinci-002 model as a case study, we generate outputs from our collection of prompts and analyze the model's generative failures. We also show the generalizability of our proposed method on other large models like BLOOM and OPT. Our results and our in-context mitigation strategies reveal open challenges for future research.

Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints

Open domain conversational agents can answer a broad range of targeted queries. However, the sequential nature of interaction with these systems makes knowledge exploration a lengthy task which burdens the user with asking a chain of well phrased questions. In this paper, we present a retrieval based system and associated dataset for predicting the next questions that the user might have. Such a system can proactively assist users in knowledge exploration leading to a more engaging dialog. The retrieval system is trained on a dataset called the Follow-up Query Bank (FQ-Bank). FQ-Bank contains ~14K multi-turn information-seeking conversations with a valid follow-up question and a set of invalid candidates. The invalid candidates are generated to simulate various syntactic and semantic confounders such as paraphrases, partial entity match, irrelevant entity, and ASR errors. We use confounder specific techniques to simulate these negative examples on the OR-QuAC dataset. Then, we train ranking models on FQ-Bank and present results comparing supervised and unsupervised approaches. The results suggest that we can retrieve the valid follow-ups by ranking them in higher positions compared to confounders, but further knowledge grounding can improve ranking performance.
FQ-Bank is publicly available at https://github.com/amazon-science/fq-bank.

Learning to Retrieve Engaging Follow-Up Queries

Recent studies have suggested that neural language models learn and store a large amount of facts and commonsense knowledge from training data. 
The ability of language models to restore such knowledge is often evaluated via zero-shot cloze-style QA tasks. 
However, such evaluations rely only on prediction accuracy without punishing the systems for their mistakes, e.g., simply guessing or hallucinating likely answers. 
Selective prediction is a more informative evaluation framework that takes the confidence of predictions into account. 
Under the selective prediction setting, a model is evaluated not only by the number of correct predictions, but also by the ability to filter out dubious predictions by estimating the confidence of individual predictions. 
Such confidence-aware evaluation is crucial for determining whether to trust zero-shot predictions of language models. 
In this paper, we apply the selective prediction setting to an existing benchmark, LAMA probe, and conduct extensive experiments with recent neural language models and different confidence functions. 
We empirically show that our Selective-LAMA evaluation is more robust to the effect of simple guesses than the conventional accuracy-based evaluation.
Our evaluation reveals the importance of the choice of confidence functions by showing that simply relying on token probabilities is not always the best choice.
Further analysis shows that various confidence functions exhibit different preferences over predicted tokens for a given context.

Selective-LAMA: Selective Prediction for Confidence-Aware Evaluation of Language Models

In this paper, we present MuFaSSa (Multi-view Faithfulness Scoring via Source Ablation), a metric for evaluating faithfulness of abstractive summaries, and for guiding training of more faithful summarizers. For evaluation, MuFaSSa employs different strategies (e.g., masking entity mentions) to first remove information from the source document to form multiple ablated views. Then, the faithfulness level of each token in a generated summary is measured by the difference between the token generation probabilities when given the original document and the ablated document as inputs to trained summarizers. For training, MuFaSSa uses a novel word truncation objective that drops unfaithful tokens located by MuFaSSa in both the decoder input and output. Alignments with human-annotated faithfulness labels on AggreFact show that MuFaSSa is comparable to or better than existing metrics built on classifiers or QA models pre-trained on other tasks. In experiments on summarization with XSum and CNN/DailyMail, models trained with word truncation using MuFaSSa outperform competitive methods according to both automatic faithfulness metrics and human assessments.

Multi-View Source Ablation for Faithful Summarization

Humor recognition has been extensively studied with different methods in the past years. However, existing studies on humor recognition do not understand the mechanisms that generate humor. In this paper, inspired by the incongruity theory, any joke can be divided into two components (the setup and the punchline). Both components have multiple possible semantics, and there is an incongruous relationship between them. We use density matrices to represent the semantic uncertainty of the setup and the punchline, respectively, and design QE-Uncertainty and QE-Incongruity with the help of quantum entropy as features for humor recognition. The experimental results on the SemEval2021 Task 7 dataset show that the proposed features are more effective than the baselines for recognizing humorous and non-humorous texts.

Mining Effective Features Using Quantum Entropy for Humor Recognition

Pretrained language models (PLMs) are trained on massive corpora, but often need to specialize to specific domains. A parameter-efficient adaptation method suggests training an adapter for each domain on the task of language modeling. This leads to good in-domain scores but can be impractical for domain- or resource-restricted settings. A solution is to use a related-domain adapter for the novel domain at test time. In this paper, we introduce AdapterSoup, an approach that performs weight-space averaging of adapters trained on different domains. Our approach is embarrassingly parallel: first, we train a set of domain-specific adapters; then, for each novel domain, we determine which adapters should be averaged at test time. 
We present extensive experiments showing that AdapterSoup consistently improves performance to new domains without extra training. We also explore weight averaging of adapters trained on the same domain with different hyper-parameters, and show that it preserves the performance of a PLM on new domains while obtaining strong in-domain results. We explore various approaches for choosing which adapters to combine, such as text clustering and semantic similarity. We find that using clustering leads to the most competitive results on novel domains.

AdapterSoup: Weight Averaging to Improve Generalization of Pretrained Language Models

In open-retrieval conversational machine reading (OR-CMR) task, machines are required to do multi-turn question answering given dialogue history and a textual knowledge base. Existing works generally utilize two independent modules to approach this problem's two successive sub-tasks: first with a hard-label decision making and second with a question generation aided by various entailment reasoning methods. Such usual cascaded modeling is vulnerable to error propagation and prevents the two sub-tasks from being consistently optimized. In this work, we instead model OR-CMR as a unified text-to-text task in a fully end-to-end style. Experiments on the ShARC and OR-ShARC dataset show the effectiveness of our proposed end-to-end framework on both sub-tasks by a large margin, achieving new state-of-the-art results. Further ablation studies support that our framework can generalize to different backbone models.

Towards End-to-End Open Conversational Machine Reading

Knowledge selection is the key in knowledge-grounded dialogues (KGD), which aims to select an appropriate knowledge snippet to be used in the utterance based on dialogue history. Previous studies mainly employ the classification approach to classify each candidate snippet as "relevant” or "irrelevant” independently. However, such approaches neglect the interactions between snippets, leading to difficulties in inferring the meaning of snippets. Moreover, they lack modeling of the discourse structure of dialogue-knowledge interactions. We propose a simple yet effective generative approach for knowledge selection, called GenKS. GenKS learns to select snippets by generating their identifiers with a sequence-to-sequence model. GenKS therefore captures intra-knowledge interaction inherently through attention mechanisms. Meanwhile, we devise a hyperlink mechanism to model the dialogue-knowledge interactions explicitly. We conduct experiments on three benchmark datasets, and verify GenKS achieves the best results on both knowledge selection and response generation.

Downloads

Next from EACL 2023

Trained on 100 million words and still in shape: BERT meets British National Corpus

.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 EACL 2023

Trained on 100 million words and still in shape: BERT meets British National Corpus

Downloads