In the rapidly evolving domain of Natural Language Generation (NLG) evaluation, introducing Large Language Models (LLMs) has opened new avenues for assessing generated content quality, e.g., coherence, creativity, and context relevance. This paper aims to provide a thorough overview of leveraging LLMs for NLG evaluation, a burgeoning area that lacks a systematic analysis. We propose a coherent taxonomy for organizing existing LLM-based evaluation metrics, offering a structured framework to understand and compare these methods. Our detailed exploration includes critically assessing various LLM-based methodologies, as well as comparing their strengths and limitations in evaluating NLG outputs. By discussing unresolved challenges, including bias, robustness, domain-specificity, and unified evaluation, this paper seeks to offer insights to researchers and advocate for fairer and more advanced NLG evaluation techniques.

Conditional question answering (CQA) is an important task that aims to find probable answers and identify missing conditions. Existing approaches struggle with CQA due to two challenges: (1) precisely identifying necessary conditions and the logical relationship, and (2) verifying conditions to detect any that are missing. In this paper, we propose a novel prompting approach, Chain of condition, by first identifying all conditions and constructing their logical relationships explicitly according to the document, then verifying whether these conditions are satisfied, finally solving the logical expression to indicate any missing conditions and generating the answer accordingly. Experiments on two CQA benchmark datasets show our chain of condition outperforms existing prompting baselines, establishing a new state of the art. Furthermore, with only a few examples, our method can facilitate GPT-3.5-Turbo or GPT-4 to outperform all existing supervised models.

Although many large-scale knowledge bases (KBs) claim to contain multilingual information, their support for many non-English languages is often incomplete. This incompleteness gives birth to the task of cross-lingual question answering over knowledge base (xKBQA), which aims to answer questions in languages different from that of the provided KB. One of the major challenges facing xKBQA is the high cost of data annotation, leading to limited resources available for further exploration. Another challenge is mapping KB schemas and natural language expressions in the questions under cross-lingual settings. In this paper, we propose a novel approach for xKBQA in a reading comprehension paradigm. We convert KB subgraphs into passages to narrow the gap between KB schemas and questions, which enables our model to benefit from recent advances in multilingual pre-trained language models (MPLMs) and cross-lingual machine reading comprehension (xMRC). Specifically, we use MPLMs, with considerable knowledge of cross-lingual mappings, for cross-lingual reading comprehension. Existing high-quality xMRC datasets can be further utilized to finetune our model, greatly alleviating the data scarcity issue in xKBQA. Extensive experiments on two xKBQA datasets in 12 languages show that our approach outperforms various baselines and achieves strong few-shot and zero-shot performance. Our dataset and code are released for further research.

The multi-answer phenomenon, where a question may have multiple answers scattered in the document, can be well handled by humans but is challenging enough for machine reading comprehension (MRC) systems. Despite recent progress in multi-answer MRC, there lacks a systematic analysis of how this phenomenon arises and how to better address it. In this work, we design a taxonomy to categorize commonly-seen multi-answer MRC instances, with which we inspect three multi-answer datasets and analyze where the multi-answer challenge comes from. We further analyze how well different paradigms of current multi-answer MRC models deal with different types of multi-answer instances. We find that some paradigms capture well the key information in the questions while others better model the relation between questions and contexts. We thus explore strategies to make the best of the strengths of different paradigms. Experiments show that generation models can be a promising platform to incorporate different paradigms. Our annotations and code are released for further research.

FEVEROUS is a fact extraction and verification task that requires systems to extract evidence of both sentences and table cells from a Wikipedia dump, then predict the veracity of the given claim accordingly. Existing works extract evidence in the two formats separately, ignoring potential connections between them. In this paper, we propose a Unified Evidence Extraction model (UnifEE), which uses a mixed evidence graph to extract the evidence in both formats. With the carefully-designed unified evidence graph, UnifEE allows evidence interactions among all candidates in both formats at similar granularity. Experiments show that, with information aggregated from related evidence candidates in the fusion graph, UnifEE can make better decisions about which evidence should be kept, especially for claims requiring multi-hop reasoning or a combination of tables and texts. Thus it outperforms all previous evidence extraction methods and brings significant improvement in the subsequent claim verification step.

Different from previous fact extraction and verification tasks that only consider evidence of a single format, FEVEROUS brings further challenges by extending the evidence format to both plain text and tables. Existing works convert all candidate evidence into either sentences or tables, thus often failing to fully capture the rich context in their original format from the converted evidence, let alone the context information lost during conversion. In this paper, we propose a Dual Channel Unified Format fact verification model (DCUF), which unifies various evidence into parallel streams, i.e., natural language sentences and a global evidence table, simultaneously. With carefully-designed evidence conversion and organization methods, DCUF makes the most of pre-trained table/language models to encourage each evidence piece to perform early and thorough interactions with other pieces in its original format. Experiments show that our model can make better use of existing pre-trained models to absorb evidence of two formats, thus outperforming previous works by a large margin. Our code and models are publicly available.

Open-ended text generation tasks, such as dialogue generation and story completion, require models to generate a coherent continuation given limited preceding context. The open-ended nature of these tasks brings new challenges to the neural auto-regressive text generators nowadays. Despite these neural models are good at producing human-like text, it is difficult for them to arrange causalities and relations between given facts and possible ensuing events. To bridge this gap, we propose a novel two-stage method which explicitly arranges the ensuing events in open-ended text generation. Our approach can be understood as a specially-trained coarse-to-fine algorithm, where an event transition planner provides a “coarse” plot skeleton and a text generator in the second stage refines the skeleton. Experiments on two open-ended text generation tasks demonstrate that our proposed method effectively improves the quality of the generated text, especially in coherence and diversity. We will release the codes to the community for further exploration.

Document-level Relation Extraction (RE) is a more challenging task than sentence RE as it often requires reasoning over multiple sentences. Yet, human annotators usually use a small number of sentences to identify the relationship between a given entity pair. In this paper, we present an embarrassingly simple but effective method to heuristically select evidence sentences for document-level RE, which can be easily combined with BiLSTM to achieve good performance on benchmark datasets, even better than fancy graph neural network based methods. We have released our code at https://github.com/AndrewZhe/Three-Sentences-Are-All-You-Need.

Chinese pre-trained language models usually process text as a sequence of characters, while ignoring more coarse granularity, e.g., words. In this work, we propose a novel pre-training paradigm for Chinese — Lattice-BERT, which explicitly incorporates word representations along with characters, thus can model a sentence in a multi-granularity manner. Specifically, we construct a lattice graph from the characters and words in a sentence and feed all these text units into transformers. We design a lattice position attention mechanism to exploit the lattice structures in self-attention layers. We further propose a masked segment prediction task to push the model to learn from rich but redundant information inherent in lattices, while avoiding learning unexpected tricks. Experiments on 11 Chinese natural language understanding tasks show that our model can bring an average increase of 1.5% under the 12-layer setting, which achieves new state-of-the-art among base-size models on the CLUE benchmarks. Further analysis shows that Lattice-BERT can harness the lattice structures, and the improvement comes from the exploration of redundant information and multi-granularity representations. Our code will be available at https://github.com/alibaba/pretrained-language-models/LatticeBERT.

In this paper, we present a new verification style reading comprehension dataset named VGaokao from Chinese Language tests of Gaokao. Different from existing efforts, the new dataset is originally designed for native speakers’ evaluation, thus requiring more advanced language understanding skills. To address the challenges in VGaokao, we propose a novel Extract-Integrate-Compete approach, which iteratively selects complementary evidence with a novel query updating mechanism and adaptively distills supportive evidence, followed by a pairwise competition to push models to learn the subtle difference among similar text pieces. Experiments show that our methods outperform various baselines on VGaokao with retrieved complementary evidence, while having the merits of efficiency and explainability. Our dataset and code are released for further research.

Traditional Key-value Memory Neural Networks (KV-MemNNs) are proved to be effective to support shallow reasoning over a collection of documents in domain specific Question Answering or Reading Comprehension tasks. However, extending KV-MemNNs to Knowledge Based Question Answering (KB-QA) is not trivia, which should properly decompose a complex question into a sequence of queries against the memory, and update the query representations to support multi-hop reasoning over the memory. In this paper, we propose a novel mechanism to enable conventional KV-MemNNs models to perform interpretable reasoning for complex questions. To achieve this, we design a new query updating strategy to mask previously-addressed memory information from the query representations, and introduce a novel STOP strategy to avoid invalid or repeated memory reading without strong annotation signals. This also enables KV-MemNNs to produce structured queries and work in a semantic parsing fashion. Experimental results on benchmark datasets show that our solution, trained with question-answer pairs only, can provide conventional KV-MemNNs models with better reasoning abilities on complex questions, and achieve state-of-art performances.

Identifying long-span dependencies between discourse units is crucial to improve discourse parsing performance. Most existing approaches design sophisticated features or exploit various off-the-shelf tools, but achieve little success. In this paper, we propose a new transition-based discourse parser that makes use of memory networks to take discourse cohesion into account. The automatically captured discourse cohesion benefits discourse parsing, especially for long span scenarios. Experiments on the RST discourse treebank show that our method outperforms traditional featured based methods, and the memory based discourse cohesion can improve the overall parsing performance significantly.