Thailand

Adapter modules were recently introduced as an efficient alternative to fine-tuning in NLP. Adapter tuning consists in freezing pre-trained parameters of a model and injecting lightweight modules between layers, resulting in the addition of only a small number of task-specific trainable parameters. While adapter tuning was investigated for multilingual neural machine translation, this paper proposes a comprehensive analysis of adapters for multilingual speech translation (ST). Starting from different pre-trained models (a multilingual ST trained on parallel data or a multilingual BART (mBART) trained on non parallel multilingual data), we show that adapters can be used to: (a) efficiently specialize ST to specific language pairs with a low extra cost in terms of parameters, and (b) transfer from an automatic speech recognition (ASR) task and an mBART pre-trained model to a multilingual ST task. Experiments show that adapter tuning offer competitive results to full fine-tuning, while being much more parameter-efficient.

ACL-IJCNLP 2021

Lightweight Adapter Tuning for Multilingual Speech Translation

multilingual st

adapters

speech translation

**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

Transformer-based language models (LMs) pretrained on large text collections implicitly store a wealth of lexical semantic knowledge, but it is non-trivial to extract that knowledge effectively from their parameters. Inspired by prior work on semantic specialization of static word embedding (WE) models, we show that it is possible to expose and enrich lexical knowledge from the LMs, that is, to specialize them to serve as effective and universal "decontextualized" word encoders even when fed input words "in isolation" (i.e., without any context). Their transformation into such word encoders is achieved through a simple and efficient lexical fine-tuning procedure (termed LexFit) based on dual-encoder network structures. Further, we show that LexFit can yield effective word encoders even with limited lexical supervision and, via cross-lingual transfer, in different languages without any readily available external knowledge. Our evaluation over four established, structurally different lexical-level tasks in 8 languages indicates the superiority of LexFit-based WEs over standard static WEs (e.g., fastText) and WEs from vanilla LMs. Other extensive experiments and ablation studies further profile the LexFit framework, and indicate best practices and performance variations across LexFit variants, languages, and lexical tasks, also directly questioning the usefulness of traditional WE models in the era of large neural models.

LexFit: Lexical Fine-Tuning of Pretrained Language Models

Recent studies on semantic frame induction show that relatively high performance has been achieved by using clustering-based methods with contextualized word embeddings. However, there are two potential drawbacks to these methods: one is that they focus too much on the superficial information of the frame-evoking verb and the other is that they tend to divide the instances of the same verb into too many different frame clusters. To overcome these drawbacks, we propose a semantic frame induction method using masked word embeddings and two-step clustering. Through experiments on the English FrameNet data, we demonstrate that using the masked word embeddings is effective for avoiding too much reliance on the surface information of frame-evoking verbs and that two-step clustering can improve the number of resulting frame clusters for the instances of the same verb.

Semantic Frame Induction using Masked Word Embeddings and Two-Step Clustering

In this paper we present the first model for directly synthesizing fluent, natural-sounding spoken audio captions for images that does not require natural language text as an intermediate representation or source of supervision. Instead, we connect the image captioning module and the speech synthesis module with a set of discrete, sub-word speech units that are discovered with a self-supervised visual grounding task. We conduct experiments on the Flickr8k spoken caption dataset in addition to a novel corpus of spoken audio captions collected for the popular MSCOCO dataset, demonstrating that our generated captions also capture diverse visual semantics of the images they describe. We investigate several different intermediate speech representations, and empirically find that the representation must satisfy several important properties to serve as drop-in replacements for text.

Text-Free Image-to-Speech Synthesis Using Learned Segmental Units

Multimodal sentiment analysis is the challenging research area that attends to the fusion of multiple heterogeneous modalities. The main challenge is the occurrence of some missing modalities during the multimodal fusion procedure. However, the existing techniques require all modalities as input, thus are sensitive to missing modalities at predicting time. In this work, the coupled-translation fusion network (CTFN) is firstly proposed to model bi-direction interplay via couple learning, ensuring the robustness in respect to missing modalities. Specifically, the cyclic consistency constraint is presented to improve the translation performance, allowing us directly to discard decoder and only embraces encoder of Transformer. This could contribute to a much lighter model. Due to the couple learning, CTFN is able to conduct bi-direction cross-modality intercorrelation parallelly. Based on CTFN, a hierarchical architecture is further established to exploit multiple bi-direction translations, leading to double multimodal fusing embeddings compared with traditional translation methods. Moreover, the convolution block is utilized to further highlight explicit interactions among those translations. For evaluation, CTFN was verified on two multimodal benchmarks with extensive ablation studies. The experiments demonstrate that the proposed framework achieves state-of-the-art or often competitive performance. Additionally, CTFN still maintains robustness when considering missing modality.

CTFN: Hierarchical Learning for Multimodal Sentiment Analysis Using Coupled-Translation Fusion Network

We introduce a novel dataset of human judgments of machine-edited text and initial models of those perceptions. Six machine-editing methods ranging from character swapping to variational autoencoders are applied to collections of English-language social media text and scientific abstracts. The edits are judged in context for detectability and the extent to which they preserve the meaning of the original. Automated measures of semantic similarity and fluency are evaluated individually and combined to produce composite models of human perception. Both meaning preservation and detectability are predicted within 6% of the upper bound of human consensus labeling.

Perceptual Models of Machine-Edited Text

Much of modern-day text simplification research focuses on sentence-level simplification, transforming original, more complex sentences into simplified versions. However, adding content can often be useful when difficult concepts and reasoning need to be explained. In this work, we present the first datadriven study of content addition in text simplification, which we call elaborative simplification. We introduce a new annotated dataset of 1.3K instances of elaborative simplification in the Newsela corpus, and analyze how entities, ideas, and concepts are elaborated through the lens of contextual specificity. We establish baselines for elaboration generation using large-scale pre-trained language models, and demonstrate that considering contextual specificity during generation can improve performance. Our results illustrate the complexities of elaborative simplification, suggesting many interesting directions for future work.

Elaborative Simplification: Content Addition and Explanation Generation in Text Simplification

A view of NPL for Dyslexics

Dynamic faceted search (DFS), an interactive query refinement technique, is a form of Human–computer information retrieval (HCIR) approach. It allows users to narrow down search results through facets, where the facets-documents mapping is determined at runtime based on the context of user query instead of pre-indexing the facets statically. In this paper, we propose a new unsupervised approach for dynamic facet generation, namely optimistic facets, which attempts to generate the best possible subset of facets, hence maximizing expected Discounted Cumulative Gain (DCG), a measure of ranking quality that uses a graded relevance scale. We also release code to generate a new evaluation dataset. Through empirical results on two datasets, we show that the proposed DFS approach considerably improves the document ranking in the search results.

Dynamic Facet Selection by Maximizing Graded Relevance

Biases and artifacts in training data can cause unwelcome behavior in text classifiers (such as shallow pattern matching), leading to lack of generalizability.
One solution to this problem is to include users in the loop and leverage their feedback to improve models.
We propose a novel explanatory debugging pipeline called \textbf{HILDIF}, enabling humans to improve deep text classifiers using influence functions as an explanation method. 
We experiment on the Natural Language Inference (NLI) task, showing that HILDIF can effectively alleviate artifact problems in fine-tuned BERT models and result in increased model generalizability.

HILDIF: Interactive Debugging of NLI Models Using Influence Functions

We present a novel interactive learning protocol that enables training request-fulfilling agents by verbally describing their activities. Our protocol gives rise to a new family of interactive learning algorithms that offer complementary advantages against traditional algorithms like imitation learning (IL) and reinforcement learning (RL). We develop an algorithm that practically implements this protocol and employ it to train agents in two challenging request-fulfilling problems using purely language-description feedback. Empirical results demonstrate the strengths of our algorithm: compared to RL baselines, it is more sample-efficient; compared to IL baselines, it achieves competitive success rates while not requiring feedback providers to have agent-specific expertise. We also provide theoretical guarantees of the algorithm under certain assumptions on the teacher and the environment.

Lightweight Adapter Tuning for Multilingual Speech Translation

Downloads

Next from ACL-IJCNLP 2021

LexFit: Lexical Fine-Tuning of Pretrained Language Models

Similar lecture

How to Split: the Effect of Word Segmentation on Gender Bias in Speech Translation