Canada

In this paper, we define a widely neglected property in dialogue text, duality, which is a hierarchical property that is reflected in human behaviours in daily conversations: Based on the logic in a conversation (or a sentence), people can infer follow-up utterances (or tokens) based on the previous text, and vice versa. We propose a hierarchical duality learning for dialogue (HDLD) to simulate this human cognitive ability, for generating high quality responses that connect both previous and follow-up dialogues. HDLD utilizes hierarchical dualities at token hierarchy and utterance hierarchy. HDLD maximizes the mutual information between past and future utterances. Thus, even if future text is invisible during inference, HDLD is capable of estimating future information implicitly based on dialogue history and generates both coherent and informative responses. In contrast to previous approaches that solely utilize future text as auxiliary information to encode during training, HDLD leverages duality to enable interaction between dialogue history and the future. This enhances the utilization of dialogue data, leading to the improvement in both automatic and human evaluation.

&lt;iframe src=&quot;https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/6f9a8787-45ca-4393-ab93-e24012e681ac&quot; width=&quot;300&quot; height=&quot;400&quot;&gt;&lt;/iframe&gt;

ACL 2023

Envisioning Future from the Past: Hierarchical Duality Learning for Multi-Turn Dialogue Generation

duality in dialogues

dual learning

dialogue generation

### Welcome to ACL 2023, the 61st Annual Meeting of the Association for Computational Linguistics! 
<br>The conference will be held in Toronto, Canada, July 9-14, 2023.<br><br>
Following the succession of the recent conferences in our field, ACL 2023 will adopt a hybrid format.
While the impact of Covid has considerably diminished in terms of traveling, obtaining visas to Canada
entails a very long process. Moreover, the global economic conditions pose challenges for many individuals to travel to conferences. Recognizing these circumstances, we know many participants may not be
able to attend the conference in person. Therefore, we are committed to providing a great virtual platform
so everyone has the opportunity to interact with other participants and enjoy the conference. Based on the
current registered participants, approxiately 30% have chosen to attend the conference virtually. Whether
you join us in person or virtually, we sincerely hope everyone has a remarkable conference experience.<br>
This General Chair’s message is where I express my gratitude to the many individuals who have made
enormous contributions to the conference over the past year.

Read [**ACL 2023 General Chair's message**](https://docs.google.com/document/d/1WobYM7norbG4dI48s75HfJoD89qgX5a_F-6U8AteLSA/edit?usp=sharing/) in full.

##### **[Conference Handbook](https://2023.aclweb.org/downloads/acl2023-handbook.pdf)**
<br><br><br><br>

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.

In this paper, we define a widely neglected property in dialogue text, duality, which is a hierarchical property that is reflected in human behaviours in daily conversations: Based on the logic in a conversation (or a sentence), people can infer follow-up utterances (or tokens) based on the previous text, and vice versa. We propose a hierarchical duality learning for dialogue (HDLD) to simulate this human cognitive ability, for generating high quality responses that connect both previous and follow-up dialogues. HDLD utilizes hierarchical dualities at token hierarchy and utterance hierarchy. HDLD maximizes the mutual information between past and future utterances. Thus, even if future text is invisible during inference, HDLD is capable of estimating future information implicitly based on dialogue history and generates both coherent and informative responses. In contrast to previous approaches that solely utilize future text as auxiliary information to encode during training, HDLD leverages duality to enable interaction between dialogue history and the future. This enhances the utilization of dialogue data, leading to the improvement in both automatic and human evaluation.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/6f9a8787-45ca-4393-ab93-e24012e681ac" width="300" height="400"></iframe>

technical paper

Zero-shot transfer learning for Dialogue State Tracking (DST) helps to handle a variety of task-oriented dialogue domains without the cost of collecting in-domain data. Existing works mainly study common data- or model-level augmentation methods to enhance the generalization but fail to effectively decouple semantics of samples, limiting the zero-shot performance of DST. In this paper, we present a simple and effective ``divide, conquer and combine'' solution, which explicitly disentangles the semantics of seen data, and leverages the performance and robustness with the mixture-of-experts mechanism. Specifically, we divide the seen data into semantically independent subsets and train corresponding experts, the newly unseen samples are mapped and inferred with mixture-of-experts with our designed ensemble inference.Extensive experiments on MultiWOZ2.1 upon T5-Adapter show our schema significantly and consistently improves the zero-shot performance, achieving the SOTA on settings without external knowledge, with only 10M trainable parameters.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/c026a1a2-09f3-41f2-b0f2-0687f20286de" width="300" height="400"></iframe>

Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking

In this paper, we present AfricaPOS, the largest part-of-speech (POS) dataset for 20 typologically diverse African languages. We discuss the challenges in annotating POS for these languages using the universal dependencies (UD) guidelines. We conducted extensive POS baseline experiments using both conditional random field and several multilingual pre-trained language models. We applied various cross-lingual transfer models trained with data available in the UD. Evaluating on the AfricaPOS dataset, we show that choosing the best transfer language(s) in both single-source and multi-source setups greatly improves the POS tagging performance of the target languages, in particular when combined with parameter-fine-tuning methods. Crucially, transferring knowledge from a language that matches the language family and morphosyntactic properties seems to be more effective for POS tagging in unseen languages.

<iframe src="https://app.sli.do/event/8PaBoicsuHK7beXFunvrtr/embed/polls/50a5f01b-4f68-4313-b5f1-0c5fc7689617" width="300" height="400"></iframe>

MasakhaPOS: Part-of-Speech Tagging for Typologically Diverse African languages

Large-scale vision-language pretrained (VLP) models like CLIP have shown remarkable performance on various downstream cross-modal tasks. However, they are usually biased towards English due to the lack of sufficient non-English image-text pairs. Existing multilingual VLP methods often learn retrieval-inefficient single-stream models by translation-augmented non-English image-text pairs. In this paper, we introduce mCLIP, a retrieval-efficient dual-stream multilingual VLP model, trained by aligning the CLIP model and a Multilingual Text Encoder (MTE) through a novel Triangle Cross-modal Knowledge Distillation (TriKD) method. It is parameter-efficient as only two light projectors on the top of them are updated during distillation. Furthermore, to enhance the token- and sentence-level multilingual representation of the MTE, we propose to train it with machine translation and contrastive learning jointly before the TriKD to provide a better initialization. Empirical results show that mCLIP achieves new state-of-the-art performance for both zero-shot and finetuned multilingual image-text retrieval task.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/79305a13-9e8a-4c8c-98a4-1dcd39be2dd0" width="300" height="400"></iframe>

mCLIP: Multilingual CLIP via Cross-lingual Transfer

Fine-tuning has been proven to be a simple and effective technique to transfer the learned knowledge of Pre-trained Language Models (PLMs) to downstream tasks. However, vanilla fine-tuning easily overfits the target data and degrades the generalization ability. Most existing studies attribute it to catastrophic forgetting, and they retain the pre-trained knowledge indiscriminately without identifying what knowledge is transferable. Motivated by this, we frame fine-tuning into a causal graph and discover that the crux of catastrophic forgetting lies in the missing causal effects from the pre-trained data. Based on the causal view, we propose a unified objective for fine-tuning to retrieve the causality back. Intriguingly, the unified objective can be seen as the sum of the vanilla fine-tuning objective, which learns new knowledge from target data, and the causal objective, which preserves old knowledge from PLMs. Therefore, our method is flexible and can mitigate negative transfer while preserving knowledge. Since endowing models with commonsense is a long-standing challenge, we implement our method on commonsense QA with a proposed heuristic estimation to verify its effectiveness. In the experiments, our method outperforms state-of-the-art fine-tuning methods on all six commonsense QA datasets and can be implemented as a plug-in module to inflate the performance of existing QA models.

<iframe src="https://app.sli.do/event/or9aypsi961h595NQtD7kk/embed/polls/55827ba6-4c6d-4dcc-aa8a-9f7a0f00cdaa" width="300" height="400"></iframe>

Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference

Many popular feature-attribution methods for interpreting deep neural networks rely on computing the gradients of a model's output with respect to its inputs.While these methods can indicate which input features may be important for the model's prediction, they reveal little about the inner workings of the model itself.In this paper, we observe that the gradient computation of a model is a special case of a more general formulation using semirings. This observation allows us to generalize the backpropagation algorithm to efficiently compute other interpretable statistics about the gradient graph of a neural network, such as the highest-weighted path and entropy. We implement this generalized algorithm, evaluate it on synthetic datasets to better understand the statistics it computes, and apply it to study BERT's behavior on the subject--verb number agreement task (SVA). With this method, we (a) validate that the amount of gradient flow through a component of a model reflects its importance to a prediction and (b) for SVA, identify which pathways of the self-attention mechanism are most important.

<iframe src="https://app.sli.do/event/oApzFnCrRo86e5qieE2QHQ/embed/polls/da09a1dc-3a61-4082-94fa-c31f872893ed" width="300" height="400"></iframe>

Generalizing Backpropagation for Gradient-Based Interpretability

Question-Answering (QA) has seen significant advances recently, achieving near human-level performance over some benchmarks. However, these advances focus on high-resourced languages such as English, while the task remains unexplored for most other languages, mainly due to the lack of annotated datasets. This work presents a native QA dataset for an East African language, Tigrinya. The dataset contains 10.6K question-answer pairs spanning 572 paragraphs extracted from 290 news articles on various topics. The dataset construction method is discussed, which is applicable to constructing similar resources for related languages. We present comprehensive experiments and analyses of several resource-efficient approaches to QA, including monolingual, cross-lingual, and multilingual setups, along with comparisons against machine-translated silver data. Our strong baseline models reach 76% in the F1 score, while the estimated human performance is 92%, indicating that the benchmark presents a good challenge for future work. We make the dataset, models, and leaderboard publicly available.

<iframe src="https://app.sli.do/event/kgQkh7cPzt9VEM52HG3MJu/embed/polls/d2c4f58e-9457-4d57-a1e5-da2d14818c47" width="300" height="400"></iframe>

Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for Tigrinya

News reports about emerging issues often include several conflicting story lines. Individual stories can be conceptualized as samples from an underlying mixture of competing narratives. The automated identification of these distinct narratives from unstructured text is a fundamental yet difficult task in Computational Linguistics since narratives are often intertwined and only implicitly conveyed in text. In this paper, we consider a more feasible proxy task: Identify the distinct sets of aligned story actors responsible for sustaining the issue-specific narratives. Discovering aligned actors, and the groups these alignments create, brings us closer to estimating the narrative that each group represents. With the help of Large Language Models (LLM), we address this task by: (i) Introducing a corpus of text segments rich in narrative content associated with six different current issues; (ii) Introducing a novel two-step graph-based framework that (a) identifies alignments between actors (INCANT) and (b) extracts aligned actor groups using the network structure (TAMPA). Amazon Mechanical Turk evaluations demonstrate the effectiveness of our framework. Across domains, alignment relationships from INCANT are accurate (macro F1 >= 0.75) and actor groups from TAMPA are preferred over 2 non-trivial baseline models (ACC >= 0.75).

<iframe src="https://app.sli.do/event/t38CPUax2NoHBQcXN6okdA/embed/polls/a1a695c7-d0d3-499c-b150-f1d5f9196fb2" width="300" height="400"></iframe>

My side, your side and the evidence: Discovering aligned actor groups and the narratives they weave

For many languages, machine translation progress is hindered by the lack of reliable training data. Models are trained on whatever pre-existing datasets may be available and then augmented with synthetic data, because it is often not economical to pay for the creation of large-scale datasets. But for the case of low-resource languages, would the creation of a few thousand professionally translated sentence pairs give any benefit? In this paper, we show that it does.We describe a broad data collection effort involving around 6k professionally translated sentence pairs for each of 39 low-resource languages, which we make publicly available. We analyse the gains of models trained on this small but high-quality data, showing that it has significant impact even when larger but lower quality pre-existing corpora are used, or when data is augmented with millions of sentences through backtranslation.

<iframe src="https://app.sli.do/event/aL2QM8dUtT8fzBuK3envdP/embed/polls/11822cda-9feb-411c-b753-2326661e14e9" width="300" height="400"></iframe>

Small Data, Big Impact: Leveraging Minimal Data for Effective Machine Translation

Selective rationales and counterfactual examples have emerged as two effective, complementary classes of interpretability methods for analyzing and training NLP models. However, prior work has not explored how these methods can be integrated to combine their complementary advantages. We overcome this limitation by introducing CREST (ContRastive Edits with Sparse raTionalization), a joint framework for selective rationalization and counterfactual text generation, and show that this framework leads to improvements in counterfactual quality, model robustness, and interpretability. First, CREST generates valid counterfactuals that are more natural than those produced by previous methods, and subsequently can be used for data augmentation at scale, reducing the need for human-generated examples. Second, we introduce a new loss function that leverages CREST counterfactuals to regularize selective rationales and show that this regularization improves both model robustness and rationale quality, compared to methods that do not leverage CREST counterfactuals. Our results demonstrate that CREST successfully bridges the gap between selective rationales and counterfactual examples, addressing the limitations of existing methods and providing a more comprehensive view of a model's predictions.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/5cc7afb1-4a0c-4403-9939-b72cfa1d517c" width="300" height="400"></iframe>

CREST: A Joint Framework for Rationalization and Counterfactual Text Generation

Tracking characters and locations throughout a story can help improve the understanding of its plot structure. Prior research has analyzed characters and locations from text independently without grounding characters to their locations in narrative time. Here, we address this gap by proposing a new spatial relationship categorization task. The objective of the task is to assign a spatial relationship category for every character and location co-mention within a window of text, taking into consideration linguistic context, narrative tense, and temporal scope. To this end, we annotate spatial relationships in approximately $2500$ book excerpts and train a model using contextual embeddings as features to predict these relationships. When applied to a set of books, this model allows us to test several hypotheses on mobility and domestic space, revealing that protagonists are more mobile than non-central characters and that women as characters tend to occupy more interior space than men. Overall, our work is the first step towards joint modeling and analysis of characters and places in narrative text.

<iframe src="https://app.sli.do/event/6qSnTPZvioRLfFJpZUjhCw/embed/polls/4a8f746d-7f73-46ad-a875-177a88c618b1" width="300" height="400"></iframe>

Downloads

Next from ACL 2023

Divide, Conquer, and Combine: Mixture of Semantic-Independent Experts for Zero-Shot Dialogue State Tracking

Similar lecture

FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue