Cross-lingual summarization (CLS) is the task to produce a summary in one particular language for a source document in a different language. Existing methods simply divide this task into two steps: summarization and translation, leading to the problem of error propagation. To handle that, we present an end-to-end CLS framework, which we refer to as Neural Cross-Lingual Summarization (NCLS), for the first time. Moreover, we propose to further improve NCLS by incorporating two related tasks, monolingual summarization and machine translation, into the training process of CLS under multi-task learning. Due to the lack of supervised CLS data, we propose a round-trip translation strategy to acquire two high-quality large-scale CLS datasets based on existing monolingual summarization datasets. Experimental results have shown that our NCLS achieves remarkable improvement over traditional pipeline methods on both English-to-Chinese and Chinese-to-English CLS human-corrected test sets. In addition, NCLS with multi-task learning can further significantly improve the quality of generated summaries. We make our dataset and code publicly available here:Rod gray , 94 , had been taken to hospital by ambulance after he cut his head in a fall at his home … Rod gray was taken to ipswich hospital after falling over at home .Rod gray was taken to Ipswich Hospital after falling down at home. MS RTT English Article (Input for MS or CLS)English Reference (Output for MS) Chinese ReferenceRod gray was taken to ipswich hospital after falling over at home .Rod-Grau wurde nach dem Sturz zu Hause ins ipswich-Krankenhaus gebracht.

No abstract

Decoding human brain activities based on linguistic representations has been actively studied in recent years. However, most previous studies exclusively focus on word-level representations, and little is learned about decoding whole sentences from brain activation patterns. This work is our effort to mend the gap. In this paper, we build decoders to associate brain activities with sentence stimulus via distributed representations, the currently dominant sentence representation approach in natural language processing (NLP). We carry out a systematic evaluation, covering both widely-used baselines and state-of-the-art sentence representation models. We demonstrate how well different types of sentence representations decode the brain activation patterns and give empirical explanations of the performance difference. Moreover, to explore how sentences are neurally represented in the brain, we further compare the sentence representation’s correspondence to different brain areas associated with high-level cognitive functions. We find the supervised structured representation models most accurately probe the language atlas of human brain. To the best of our knowledge, this work is the first comprehensive evaluation of distributed sentence representations for brain decoding. We hope this work can contribute to decoding brain activities with NLP representation models, and understanding how linguistic items are neurally represented.

Neuroimaging studies have found that theory of mind (ToM) and discourse comprehension involve similar brain regions. These brain regions may be associated with three cognitive components that are necessarily or frequently involved in ToM and discourse comprehension, including social concept representation and retrieval, domain-general semantic integration, and domain-specific integration of social semantic contents. Using fMRI, we investigated the neural correlates of these three cognitive components by exploring how discourse topic (social/nonsocial) and discourse processing period (ending/beginning) modulate brain activation in a discourse comprehension (and also ToM) task. Different sets of brain areas showed sensitivity to discourse topic, discourse processing period, and the interaction between them, respectively. The most novel finding was that the right temporoparietal junction and middle temporal gyrus showed sensitivity to discourse processing period only during social discourse comprehension, indicating that they selectively contribute to domain-specific semantic integration. Our finding indicates how different domains of semantic information are processed and integrated in the brain and provides new insights into the neural correlates of ToM and discourse comprehension.